[{"data":1,"prerenderedAt":1132},["ShallowReactive",2],{"blog-\u002Fblog\u002Fgive-your-agent-live-web-context":3,"blog-related-\u002Fblog\u002Fgive-your-agent-live-web-context":863},{"id":4,"title":5,"author":6,"body":7,"category":847,"cover":848,"description":849,"draft":850,"extension":851,"image":847,"launchCta":847,"meta":852,"navigation":853,"ogImage":847,"path":854,"publishedAt":855,"readTime":847,"seo":856,"stem":857,"tags":858,"updatedAt":847,"__hash__":862},"blogUnlisted\u002Fblog\u002Fgive-your-agent-live-web-context.md","Give Your AI Agent Live Web Context in One Call","The Monid Team",{"type":8,"value":9,"toc":829},"minimark",[10,15,85,98,103,152,156,159,166,170,185,189,194,203,210,219,223,280,288,292,295,337,344,348,351,379,382,476,483,487,499,597,609,613,622,628,638,645,666,672,726,730,751,755,762,774,792,803,807,825],[11,12,14],"p",{"style":13},"font-size:18px !important;line-height:1.65 !important;margin:0 0 24px;color:inherit;","Copy this line to your agent to give your agent live web search.",[16,17,22],"pre",{"className":18,"code":19,"language":20,"meta":21,"style":21},"language-sh shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","set up https:\u002F\u002Fmonid.ai\u002FSKILL.md and use exa to search the live web and extract page content for an agent\n","sh","",[23,24,25],"code",{"__ignoreMap":21},[26,27,30,34,38,41,44,47,50,53,56,59,62,65,67,70,73,76,79,82],"span",{"class":28,"line":29},"line",1,[26,31,33],{"class":32},"s2Zo4","set",[26,35,37],{"class":36},"sfazB"," up",[26,39,40],{"class":36}," https:\u002F\u002Fmonid.ai\u002FSKILL.md",[26,42,43],{"class":36}," and",[26,45,46],{"class":36}," use",[26,48,49],{"class":36}," exa",[26,51,52],{"class":36}," to",[26,54,55],{"class":36}," search",[26,57,58],{"class":36}," the",[26,60,61],{"class":36}," live",[26,63,64],{"class":36}," web",[26,66,43],{"class":36},[26,68,69],{"class":36}," extract",[26,71,72],{"class":36}," page",[26,74,75],{"class":36}," content",[26,77,78],{"class":36}," for",[26,80,81],{"class":36}," an",[26,83,84],{"class":36}," agent\n",[11,86,87,88,97],{},"You can give an AI agent live web context with a single call: send a question to Exa's ",[89,90,94],"a",{"href":91,"rel":92},"https:\u002F\u002Fexa.ai\u002Fdocs\u002Freference\u002Fsearch",[93],"nofollow",[23,95,96],{},"\u002Fsearch"," endpoint on Monid, ask it to inline the page contents, and pipe the clean text straight back into the model. One request does the searching and the extracting, so your agent gets fresh, readable sources without a scraper, a search key, or an HTML parser anywhere in the loop. Monid is a pay-per-call data API marketplace: one integration and one wallet reach hundreds of external data endpoints across search, scraping, enrichment, and social data. This walkthrough builds one research step an agent can call whenever its training data runs out, and every command is copy-paste ready.",[99,100,102],"h2",{"id":101},"tldr","TL;DR",[104,105,106,113,120,135,149],"ul",{},[107,108,109,110,112],"li",{},"A model's weights are frozen at training time, so any question about this week needs an outside fetch. Exa's ",[23,111,96],{}," on Monid is that fetch.",[107,114,115,116,119],{},"The ",[23,117,118],{},"contents"," field turns search into search-and-extract: one call returns ranked URLs plus the actual page text, so you skip the separate scrape step most stacks bolt on.",[107,121,122,123,126,127,130,131,134],{},"Ask for ",[23,124,125],{},"text",", ",[23,128,129],{},"highlights",", or a per-source ",[23,132,133],{},"summary"," and you hand the model exactly what fits its context window instead of raw HTML.",[107,136,137,138,126,141,144,145,148],{},"Filters like ",[23,139,140],{},"type",[23,142,143],{},"category",", and ",[23,146,147],{},"startPublishedDate"," run server-side, so a \"what changed this week\" query stays tight and cheap.",[107,150,151],{},"Monid ships as an MCP server, so an agent can discover, inspect, and run this step itself. Billing is per call, so a research tool that runs all day stays in single-digit dollars.",[99,153,155],{"id":154},"the-worked-example-an-agent-that-needs-this-weeks-answer","The worked example: an agent that needs this week's answer",[11,157,158],{},"Picture an agent fielding \"What did the latest OpenAI DevDay announce?\" Its weights were frozen months ago, so it either guesses or admits it does not know. The fix is a research step: the moment the agent hits a question outside its training window, it calls out for fresh sources, reads them, and answers from what it just read. That is exactly the shape of one Exa search-and-extract call.",[11,160,161],{},[162,163],"img",{"alt":164,"src":165},"An agent hits a question its training cannot answer, makes one exa \u002Fsearch call with contents inline, which returns clean page text, highlights, and per-source summaries, all fed back as a grounded answer","\u002Fimg\u002Fblog\u002Fgive-your-agent-live-web-context-fig-exa-onecall.png",[99,167,169],{"id":168},"why-one-endpoint-instead-of-a-search-api-plus-a-scraper","Why one endpoint instead of a search API plus a scraper",[11,171,172,173,178,179,181,182,184],{},"The usual way to build this is two vendors: a search API to get URLs, then a scraping or extraction service to turn each URL into text a model can read. That means two keys, two bills, two failure modes, and a lot of glue for retries, rate limits, and messy HTML. ",[89,174,177],{"href":175,"rel":176},"https:\u002F\u002Fexa.ai",[93],"Exa"," collapses both halves into one request. Its ",[23,180,96],{}," does neural and keyword retrieval and, when you set the ",[23,183,118],{}," field, returns the cleaned page body in the same response. Your agent never sees raw markup and never touches a second service.",[99,186,188],{"id":187},"set-up-once","Set up once",[190,191,193],"h3",{"id":192},"for-agents","For agents",[11,195,196,197,202],{},"Grab an API key at ",[89,198,201],{"href":199,"rel":200},"https:\u002F\u002Fapp.monid.ai\u002F",[93],"app.monid.ai",", then paste this to your agent and hand it the key:",[16,204,208],{"className":205,"code":207,"language":125},[206],"language-text","set up https:\u002F\u002Fmonid.ai\u002FSKILL.md\n",[23,209,207],{"__ignoreMap":21},[11,211,212,213,218],{},"It learns the whole discover, inspect, run workflow itself. More details in the ",[89,214,217],{"href":215,"rel":216},"https:\u002F\u002Fmonid.ai\u002Fdocs\u002Fguide\u002Fquickstart-skill",[93],"agent quickstart",".",[190,220,222],{"id":221},"for-humans","For humans",[16,224,228],{"className":225,"code":226,"language":227,"meta":21,"style":21},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","npm install -g @monid-ai\u002Fcli\nmonid keys add --label main --key \u003Cyour-api-key>\n","bash",[23,229,230,245],{"__ignoreMap":21},[26,231,232,236,239,242],{"class":28,"line":29},[26,233,235],{"class":234},"sBMFI","npm",[26,237,238],{"class":36}," install",[26,240,241],{"class":36}," -g",[26,243,244],{"class":36}," @monid-ai\u002Fcli\n",[26,246,248,251,254,257,260,263,266,270,273,277],{"class":28,"line":247},2,[26,249,250],{"class":234},"monid",[26,252,253],{"class":36}," keys",[26,255,256],{"class":36}," add",[26,258,259],{"class":36}," --label",[26,261,262],{"class":36}," main",[26,264,265],{"class":36}," --key",[26,267,269],{"class":268},"sMK4o"," \u003C",[26,271,272],{"class":36},"your-api-ke",[26,274,276],{"class":275},"sTEyZ","y",[26,278,279],{"class":268},">\n",[11,281,282,283,218],{},"More details in the ",[89,284,287],{"href":285,"rel":286},"https:\u002F\u002Fmonid.ai\u002Fdocs\u002Fguide\u002Fquickstart-cli",[93],"CLI quickstart",[99,289,291],{"id":290},"step-1-find-the-endpoint","Step 1: Find the endpoint",[11,293,294],{},"Search the catalog for the capability. Discovery is free and returns endpoints ranked with provider, description, price, and a verified tag.",[16,296,298],{"className":225,"code":297,"language":227,"meta":21,"style":21},"monid discover -q \"web search content extraction\"\n# -> exa \u002Fsearch      (verified, search + extract in one call)\n#    exa \u002Fcontents     (verified, extract when you already have URLs)\n#    plus other extractors, ranked\n",[23,299,300,319,325,331],{"__ignoreMap":21},[26,301,302,304,307,310,313,316],{"class":28,"line":29},[26,303,250],{"class":234},[26,305,306],{"class":36}," discover",[26,308,309],{"class":36}," -q",[26,311,312],{"class":268}," \"",[26,314,315],{"class":36},"web search content extraction",[26,317,318],{"class":268},"\"\n",[26,320,321],{"class":28,"line":247},[26,322,324],{"class":323},"sHwdD","# -> exa \u002Fsearch      (verified, search + extract in one call)\n",[26,326,328],{"class":28,"line":327},3,[26,329,330],{"class":323},"#    exa \u002Fcontents     (verified, extract when you already have URLs)\n",[26,332,334],{"class":28,"line":333},4,[26,335,336],{"class":323},"#    plus other extractors, ranked\n",[11,338,339,340,343],{},"The top hit, ",[23,341,342],{},"exa \u002Fsearch",", is the one you want for an agent that starts from a question rather than a list of links.",[99,345,347],{"id":346},"step-2-read-the-schema-before-you-spend","Step 2: Read the schema before you spend",[11,349,350],{},"Inspect the endpoint to see its real input fields and current price. This step is free, and it is where you confirm field names instead of guessing them.",[16,352,354],{"className":225,"code":353,"language":227,"meta":21,"style":21},"monid inspect -p exa -e \u002Fsearch\n# -> input schema + per-call price (free)\n",[23,355,356,374],{"__ignoreMap":21},[26,357,358,360,363,366,368,371],{"class":28,"line":29},[26,359,250],{"class":234},[26,361,362],{"class":36}," inspect",[26,364,365],{"class":36}," -p",[26,367,49],{"class":36},[26,369,370],{"class":36}," -e",[26,372,373],{"class":36}," \u002Fsearch\n",[26,375,376],{"class":28,"line":247},[26,377,378],{"class":323},"# -> input schema + per-call price (free)\n",[11,380,381],{},"The fields that matter for an agent research step:",[104,383,384,390,417,423,441,449,458],{},[107,385,386,389],{},[23,387,388],{},"query",": the natural-language question. This is the only required field.",[107,391,392,394,395,398,399,402,403,126,406,144,409,412,413,416],{},[23,393,140],{},": retrieval mode, from ",[23,396,397],{},"instant"," and ",[23,400,401],{},"fast"," up through ",[23,404,405],{},"neural",[23,407,408],{},"deep",[23,410,411],{},"deep-reasoning",". Default ",[23,414,415],{},"auto"," picks for you; reach for a deeper mode when the question is broad.",[107,418,419,422],{},[23,420,421],{},"numResults",": how many sources to pull back, from 1 to 100. Keep it small for an agent, since a few strong sources beat a wall of text.",[107,424,425,427,428,126,431,126,434,126,437,440],{},[23,426,143],{},": narrow to ",[23,429,430],{},"news",[23,432,433],{},"research paper",[23,435,436],{},"company",[23,438,439],{},"financial report",", and more when the question has an obvious shape.",[107,442,443,398,445,448],{},[23,444,147],{},[23,446,447],{},"endPublishedDate",": ISO date-time bounds that keep a \"this week\" query from surfacing year-old pages.",[107,450,451,398,454,457],{},[23,452,453],{},"includeDomains",[23,455,456],{},"excludeDomains",": whitelist or blacklist sources to trust.",[107,459,460,462,463,465,466,469,470,472,473,475],{},[23,461,118],{},": the field that makes this one call instead of two. It carries ",[23,464,125],{}," (optionally with ",[23,467,468],{},"maxCharacters","), ",[23,471,129],{}," (the most relevant lines for a sub-query), and ",[23,474,133],{}," (a per-source condensation).",[11,477,478,479,482],{},"There is also ",[23,480,481],{},"outputSchema",", which asks Exa to synthesize a single structured JSON object across all the sources it read. That is the difference between handing your model a pile of pages and handing it a filled-in answer.",[99,484,486],{"id":485},"step-3-make-the-one-call","Step 3: Make the one call",[11,488,489,490,492,493,495,496,498],{},"This is the only step that bills. Pass the agent's question as ",[23,491,388],{},", cap the pull with ",[23,494,421],{},", scope it to fresh news, and set ",[23,497,118],{}," so the response already carries readable text.",[16,500,502],{"className":225,"code":501,"language":227,"meta":21,"style":21},"monid run -p exa -e \u002Fsearch \\\n  -i '{\"query\": \"OpenAI DevDay 2026 announcements\",\n       \"type\": \"neural\",\n       \"category\": \"news\",\n       \"numResults\": 5,\n       \"startPublishedDate\": \"2026-07-01T00:00:00Z\",\n       \"contents\": {\"text\": {\"maxCharacters\": 1500},\n                    \"highlights\": {\"query\": \"new products announced\", \"numSentences\": 2}}}' \\\n  -w\n# -> five recent news URLs, each with up to 1500 chars of clean body text\n#    and the two sentences most relevant to \"new products announced\",\n#    plus a costDollars breakdown for the request\n",[23,503,504,523,534,539,544,550,556,562,573,579,585,591],{"__ignoreMap":21},[26,505,506,508,511,513,515,517,520],{"class":28,"line":29},[26,507,250],{"class":234},[26,509,510],{"class":36}," run",[26,512,365],{"class":36},[26,514,49],{"class":36},[26,516,370],{"class":36},[26,518,519],{"class":36}," \u002Fsearch",[26,521,522],{"class":275}," \\\n",[26,524,525,528,531],{"class":28,"line":247},[26,526,527],{"class":36},"  -i",[26,529,530],{"class":268}," '",[26,532,533],{"class":36},"{\"query\": \"OpenAI DevDay 2026 announcements\",\n",[26,535,536],{"class":28,"line":327},[26,537,538],{"class":36},"       \"type\": \"neural\",\n",[26,540,541],{"class":28,"line":333},[26,542,543],{"class":36},"       \"category\": \"news\",\n",[26,545,547],{"class":28,"line":546},5,[26,548,549],{"class":36},"       \"numResults\": 5,\n",[26,551,553],{"class":28,"line":552},6,[26,554,555],{"class":36},"       \"startPublishedDate\": \"2026-07-01T00:00:00Z\",\n",[26,557,559],{"class":28,"line":558},7,[26,560,561],{"class":36},"       \"contents\": {\"text\": {\"maxCharacters\": 1500},\n",[26,563,565,568,571],{"class":28,"line":564},8,[26,566,567],{"class":36},"                    \"highlights\": {\"query\": \"new products announced\", \"numSentences\": 2}}}",[26,569,570],{"class":268},"'",[26,572,522],{"class":275},[26,574,576],{"class":28,"line":575},9,[26,577,578],{"class":36},"  -w\n",[26,580,582],{"class":28,"line":581},10,[26,583,584],{"class":323},"# -> five recent news URLs, each with up to 1500 chars of clean body text\n",[26,586,588],{"class":28,"line":587},11,[26,589,590],{"class":323},"#    and the two sentences most relevant to \"new products announced\",\n",[26,592,594],{"class":28,"line":593},12,[26,595,596],{"class":323},"#    plus a costDollars breakdown for the request\n",[11,598,115,599,602,603,605,606,608],{},[23,600,601],{},"-w"," flag waits inline so the call returns the results in one shot, which is what an agent tool wants. Setting ",[23,604,468],{}," keeps each source inside a slice of the context window, and the ",[23,607,129],{}," sub-query pre-selects the lines worth reading, so the model spends its attention on signal.",[99,610,612],{"id":611},"step-4-feed-the-results-back-to-the-model","Step 4: Feed the results back to the model",[11,614,615,616,618,619,621],{},"The payload from step 3 is already model-ready. Each result carries the URL, the title, the extracted ",[23,617,125],{},", and the ",[23,620,129],{},", so you concatenate them into a context block and prepend it to the agent's prompt:",[16,623,626],{"className":624,"code":625,"language":125},[206],"Sources (fetched live):\n[1] \u003Ctitle> (\u003Curl>)\n\u003Chighlights and text>\n[2] ...\n\nUsing only the sources above, answer: What did OpenAI DevDay 2026 announce?\nCite each claim with its [n].\n",[23,627,625],{"__ignoreMap":21},[11,629,630,631,633,634,637],{},"Now the model answers from what it just read, and every claim traces to a URL you can show. If you would rather skip the prompt plumbing entirely, set ",[23,632,481],{}," on the call and Exa returns a structured object (say, ",[23,635,636],{},"{announcements: [...], date, source_urls}",") that your code drops straight into the response.",[99,639,641,642],{"id":640},"when-you-already-have-the-urls-contents","When you already have the URLs: ",[23,643,644],{},"\u002Fcontents",[11,646,647,648,654,655,658,659,126,661,144,663,665],{},"Sometimes the agent is not searching, it is following a link a user pasted or a citation it found earlier. For that, Exa's ",[89,649,652],{"href":650,"rel":651},"https:\u002F\u002Fexa.ai\u002Fdocs\u002Freference\u002Fget-contents",[93],[23,653,644],{}," endpoint takes a list of ",[23,656,657],{},"urls"," and returns the same clean ",[23,660,125],{},[23,662,129],{},[23,664,133],{},", no query needed. It handles JavaScript-rendered pages and PDFs, so it is the extract half of the pipeline on its own, at a lower per-call rate than a full search.",[11,667,668],{},[162,669],{"alt":670,"src":671},"A decision split: if the agent does not know the URLs yet it calls exa \u002Fsearch, if it already has them it calls exa \u002Fcontents, and both return the same clean text that feeds into the agent context","\u002Fimg\u002Fblog\u002Fgive-your-agent-live-web-context-fig-exa-route.png",[16,673,675],{"className":225,"code":674,"language":227,"meta":21,"style":21},"monid run -p exa -e \u002Fcontents \\\n  -i '{\"urls\": [\"https:\u002F\u002Fopenai.com\u002Fblog\u002Fdevday-2026\"],\n       \"text\": {\"maxCharacters\": 2000},\n       \"summary\": {\"query\": \"key announcements\"}}' \\\n  -w\n# -> clean body text plus a one-paragraph summary for that URL\n",[23,676,677,694,703,708,717,721],{"__ignoreMap":21},[26,678,679,681,683,685,687,689,692],{"class":28,"line":29},[26,680,250],{"class":234},[26,682,510],{"class":36},[26,684,365],{"class":36},[26,686,49],{"class":36},[26,688,370],{"class":36},[26,690,691],{"class":36}," \u002Fcontents",[26,693,522],{"class":275},[26,695,696,698,700],{"class":28,"line":247},[26,697,527],{"class":36},[26,699,530],{"class":268},[26,701,702],{"class":36},"{\"urls\": [\"https:\u002F\u002Fopenai.com\u002Fblog\u002Fdevday-2026\"],\n",[26,704,705],{"class":28,"line":327},[26,706,707],{"class":36},"       \"text\": {\"maxCharacters\": 2000},\n",[26,709,710,713,715],{"class":28,"line":333},[26,711,712],{"class":36},"       \"summary\": {\"query\": \"key announcements\"}}",[26,714,570],{"class":268},[26,716,522],{"class":275},[26,718,719],{"class":28,"line":546},[26,720,578],{"class":36},[26,722,723],{"class":28,"line":552},[26,724,725],{"class":323},"# -> clean body text plus a one-paragraph summary for that URL\n",[99,727,729],{"id":728},"what-a-research-tool-costs","What a research tool costs",[11,731,732,733,735,736,738,739,744,745,747,748,750],{},"Both endpoints bill per call, not per token or per page, so the cost of a research step is a flat, predictable unit you know before you run it. A single ",[23,734,96],{}," with inline contents is one charged call regardless of how many results you asked for, and ",[23,737,644],{}," is cheaper still because it skips the retrieval half. An agent that fires a handful of research calls per session stays in fractions of a cent to a few cents per session, and a tool running those all day lands in single-digit dollars. Current per-endpoint pricing lives at ",[89,740,743],{"href":741,"rel":742},"https:\u002F\u002Fmonid.ai\u002Ftools",[93],"monid.ai\u002Ftools",", and because inspect shows the price before you run, there are no surprises. Widen ",[23,746,421],{}," or reach for a ",[23,749,408],{}," search mode when a question is hard, keep it lean when it is not, and the bill tracks the work.",[99,752,754],{"id":753},"faq","FAQ",[11,756,757,761],{},[758,759,760],"strong",{},"Do I need an Exa API key, a search key, and a scraper?","\nNo. You integrate Monid once and fund one pay-as-you-go wallet. That single wallet reaches Exa's search and extraction endpoints, so there is no separate key for retrieval and none for parsing.",[11,763,764,767,768,770,771,773],{},[758,765,766],{},"How does one call do both search and extraction?","\nExa's ",[23,769,96],{}," takes a ",[23,772,118],{}," object alongside the query. Set it and the response includes the cleaned page text, highlights, or a summary for each result, so the searching and the reading happen in the same request.",[11,775,776,779,780,782,783,785,786,788,789,791],{},[758,777,778],{},"How do I keep results fresh instead of stale?","\nUse ",[23,781,147],{}," (and optionally ",[23,784,447],{},") to bound the window, and set ",[23,787,143],{}," to ",[23,790,430],{}," for current events. Both filters run server-side, so the agent only ever sees pages from the range you asked for.",[11,793,794,797,798,218],{},[758,795,796],{},"Can the agent run this itself?","\nYes. Monid ships as an MCP server, so an agent handed a question it cannot answer from memory can discover the endpoint, inspect the schema, and make the call on its own. See ",[89,799,802],{"href":800,"rel":801},"https:\u002F\u002Fmonid.ai\u002FSKILL.md",[93],"monid.ai\u002FSKILL.md",[99,804,806],{"id":805},"try-it","Try it",[11,808,809,810,813,814,816,817,819,820,218],{},"Run a free ",[23,811,812],{},"monid discover"," for \"web search content extraction\", inspect ",[23,815,342],{}," to confirm the fields and price, then make one call with ",[23,818,118],{}," set on a question you know the answer to. If the extracted text lines up with what you would find opening the pages yourself, wrap it as your agent's research tool and let the model call it whenever its training runs out. Start at ",[89,821,824],{"href":822,"rel":823},"https:\u002F\u002Fmonid.ai",[93],"monid.ai",[826,827,828],"style",{},"html pre.shiki code .s2Zo4, html code.shiki .s2Zo4{--shiki-light:#6182B8;--shiki-default:#82AAFF;--shiki-dark:#82AAFF}html pre.shiki code .sfazB, html code.shiki .sfazB{--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D}html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html pre.shiki code .sBMFI, html code.shiki .sBMFI{--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B}html pre.shiki code .sMK4o, html code.shiki .sMK4o{--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF}html pre.shiki code .sTEyZ, html code.shiki .sTEyZ{--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8}html pre.shiki code .sHwdD, html code.shiki .sHwdD{--shiki-light:#90A4AE;--shiki-light-font-style:italic;--shiki-default:#546E7A;--shiki-default-font-style:italic;--shiki-dark:#676E95;--shiki-dark-font-style:italic}",{"title":21,"searchDepth":247,"depth":247,"links":830},[831,832,833,834,838,839,840,841,842,844,845,846],{"id":101,"depth":247,"text":102},{"id":154,"depth":247,"text":155},{"id":168,"depth":247,"text":169},{"id":187,"depth":247,"text":188,"children":835},[836,837],{"id":192,"depth":327,"text":193},{"id":221,"depth":327,"text":222},{"id":290,"depth":247,"text":291},{"id":346,"depth":247,"text":347},{"id":485,"depth":247,"text":486},{"id":611,"depth":247,"text":612},{"id":640,"depth":247,"text":843},"When you already have the URLs: \u002Fcontents",{"id":728,"depth":247,"text":729},{"id":753,"depth":247,"text":754},{"id":805,"depth":247,"text":806},null,"\u002Fimg\u002Fblog\u002Fgive-your-agent-live-web-context.png","A hands-on tutorial: wire an AI agent to fresh web results with one Exa search-and-extract call on Monid, and feed grounded context straight back into its answer.",false,"md",{},true,"\u002Fblog\u002Fgive-your-agent-live-web-context","2026-07-09",{"title":5,"description":849},"blog\u002Fgive-your-agent-live-web-context",[859,860,861],"data","agents","search","KRRrTV2_VNzHRAUxHuqbfprkbPIEbtc_woMVkyOD-6Q",[864,925,993,1059],{"id":865,"title":866,"author":847,"body":867,"category":847,"cover":912,"description":21,"draft":850,"extension":851,"image":847,"launchCta":913,"meta":916,"navigation":853,"ogImage":847,"path":917,"publishedAt":918,"readTime":847,"seo":919,"stem":920,"tags":921,"updatedAt":847,"__hash__":924},"blog\u002Fblog\u002Fakta-pro-is-now-available-on-monid.md","Introducing private markets\ndata for agents",{"type":8,"value":868,"toc":908},[869,873,881,884,888,895,902,905],[99,870,872],{"id":871},"what-is-aktapro","What is akta.pro",[11,874,875,880],{},[89,876,879],{"href":877,"rel":878},"https:\u002F\u002Fwww.akta.pro\u002F",[93],"akta.pro"," is a private company data and signals API for\nAI agents. Company Database covers 20M+ companies with 75+ structured fields\neach. News Signals delivers deduplicated, entity-resolved company news,\nindustry news, and signals on open-ended topics, all scored for impact and\nsentiment.",[11,882,883],{},"Private-company research is usually scattered across databases, news feeds,\nreview sites, and web search. akta.pro turns that into structured API calls, so\nan agent gets the right company context and keeps moving.",[99,885,887],{"id":886},"what-is-monid","What is Monid",[11,889,890,894],{},[89,891,893],{"href":822,"rel":892},[93],"Monid"," is the tool layer for agents. It lets agents connect\nto all the tools and APIs they need, without managing signups, API keys, or\nsubscriptions.",[11,896,897,898,218],{},"Today, Monid provides tools for social media scraping, web search, image and\nmusic generation, people data search, weather APIs, ",[89,899,901],{"href":741,"rel":900},[93],"and more",[903,904],"hr",{},[11,906,907],{},"On Monid, akta.pro becomes available as part of that same layer. Your agent can\nrequest private-company context, call akta.pro through Monid, receive structured\nmarket data, and continue the task. Private markets research should feel like\nany other tool call: describe the company or sector, get the signal, keep\nbuilding.",{"title":21,"searchDepth":247,"depth":247,"links":909},[910,911],{"id":871,"depth":247,"text":872},{"id":886,"depth":247,"text":887},"\u002Fimg\u002Fblog\u002Fakta-pro-is-now-available-on-monid-v2.png",{"label":914,"command":915},"Give your agent this line to get started.","set up https:\u002F\u002Fmonid.ai\u002FSKILL.md and use akta.pro to research recent news, company enrichment, and alternative signals for Databricks",{},"\u002Fblog\u002Fakta-pro-is-now-available-on-monid","2026-07-07",{"title":866,"description":21},"blog\u002Fakta-pro-is-now-available-on-monid",[860,922,923,859],"partner-tools","private-markets","yZnqIVof0gIpw9VH6HcE3rzit5OdTvPyC6k--T1kYa8",{"id":926,"title":927,"author":847,"body":928,"category":847,"cover":982,"description":983,"draft":850,"extension":851,"image":847,"launchCta":847,"meta":984,"navigation":853,"ogImage":847,"path":985,"publishedAt":986,"readTime":847,"seo":987,"stem":988,"tags":989,"updatedAt":847,"__hash__":992},"blog\u002Fblog\u002Fyour-claude-code-can-now-make-phone-calls.md","Your Claude Code can now make phone calls",{"type":8,"value":929,"toc":978},[930,933,942,946,954,957,959,964,970,972,975],[11,931,932],{"style":13},"Copy this line to your agent to make your first phone call.",[16,934,936],{"className":18,"code":935,"language":20,"meta":21,"style":21},"set up https:\u002F\u002Fmonid.ai\u002FSKILL.md and use Saperly to call my phone number to confirm the connection works\n",[23,937,938],{"__ignoreMap":21},[26,939,940],{"class":28,"line":29},[26,941,935],{},[99,943,945],{"id":944},"what-is-saperly","What is Saperly",[11,947,948,953],{},[89,949,952],{"href":950,"rel":951},"https:\u002F\u002Fsaperly.com\u002F",[93],"Saperly"," is phone infrastructure for AI agents. It gives\nan agent a real phone number with voice, SMS, routing, spend controls, and\ncompliance built in, without making the builder manage carrier accounts or\ntelephony paperwork.",[11,955,956],{},"Your agent can confirm an appointment, follow up on a lead, check availability,\nor route a conversation without leaving the workflow it is already running.",[99,958,887],{"id":886},[11,960,961,894],{},[89,962,893],{"href":822,"rel":963},[93],[11,965,966,967,218],{},"Today, Monid provides tools for social media scraping, web search, image \u002F\nmusic \u002F 3d model generation, people data search, weather APIs, ",[89,968,901],{"href":741,"rel":969},[93],[903,971],{},[11,973,974],{},"On Monid, Saperly becomes available as part of that same layer. Your agent can\nrequest a phone call, use Saperly through Monid, receive the result, and keep\ngoing. Calling should feel like any other tool call: describe the outcome, let\nthe agent handle the phone work, and continue the task.",[826,976,977],{},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"title":21,"searchDepth":247,"depth":247,"links":979},[980,981],{"id":944,"depth":247,"text":945},{"id":886,"depth":247,"text":887},"\u002Fimg\u002Fblog\u002Fyour-claude-code-can-now-make-phone-calls.png","Saperly is now available on Monid. Your agent can now make phone calls for you.",{},"\u002Fblog\u002Fyour-claude-code-can-now-make-phone-calls","2026-07-05",{"title":927,"description":983},"blog\u002Fyour-claude-code-can-now-make-phone-calls",[860,922,990,991],"voice","phone","X0vLpqb1Vn9mIFY4XAQ16a67_nbOfiZV8NEdV12nu1A",{"id":994,"title":995,"author":847,"body":996,"category":847,"cover":1048,"description":1049,"draft":850,"extension":851,"image":847,"launchCta":847,"meta":1050,"navigation":853,"ogImage":847,"path":1051,"publishedAt":1052,"readTime":847,"seo":1053,"stem":1054,"tags":1055,"updatedAt":847,"__hash__":1058},"blog\u002Fblog\u002Fintroducing-suzanne-chatgpt-for-3d-models.md","Introducing\nClaude for 3D models",{"type":8,"value":997,"toc":1044},[998,1001,1010,1014,1022,1025,1027,1032,1037,1039,1042],[11,999,1000],{"style":13},"Copy this line to your agent to generate your 3D model.",[16,1002,1004],{"className":18,"code":1003,"language":20,"meta":21,"style":21},"set up https:\u002F\u002Fmonid.ai\u002FSKILL.md and create a 3D model for a rabbit\n",[23,1005,1006],{"__ignoreMap":21},[26,1007,1008],{"class":28,"line":29},[26,1009,1003],{},[99,1011,1013],{"id":1012},"what-is-suzanne","What is Suzanne",[11,1015,1016,1021],{},[89,1017,1020],{"href":1018,"rel":1019},"https:\u002F\u002Fwww.suzanne3d.com",[93],"Suzanne"," is an AI-native 3D modeling tool that turns a prompt into a\nusable 3D asset. Instead of opening a modeling tool, blocking out forms,\nadding details, and exporting by hand, you describe what you want and let\nSuzanne generate the model for you.",[11,1023,1024],{},"That changes who can create 3D objects. Product teams can prototype visual\nideas faster. Game builders can rough out props and characters without\nwaiting on a full art pass. Agents can generate assets as part of a larger\nworkflow, then hand those files to downstream tools for rendering, testing,\nor iteration.",[99,1026,887],{"id":886},[11,1028,1029,894],{},[89,1030,893],{"href":822,"rel":1031},[93],[11,1033,897,1034,218],{},[89,1035,901],{"href":741,"rel":1036},[93],[903,1038],{},[11,1040,1041],{},"On Monid, Suzanne becomes available as part of that same layer. Your agent can\nask for the 3D asset it needs, call Suzanne through Monid, and continue the task.\n3D creation should feel as direct as text generation: describe the thing, get\nthe artifact, keep building.",[826,1043,977],{},{"title":21,"searchDepth":247,"depth":247,"links":1045},[1046,1047],{"id":1012,"depth":247,"text":1013},{"id":886,"depth":247,"text":887},"\u002Fimg\u002Fblog\u002Fintroducing-suzanne-chatgpt-for-3d-models.png","Suzanne is now available on Monid. Turn any idea into a production-ready 3D model in one prompt.",{},"\u002Fblog\u002Fintroducing-suzanne-chatgpt-for-3d-models","2026-06-25",{"title":995,"description":1049},"blog\u002Fintroducing-suzanne-chatgpt-for-3d-models",[1056,860,1057],"3d","creative-tools","_S0uHM_dNVZKt_1ohYV4hn2Fm6SMxsDxzSezZf6lYFQ",{"id":1060,"title":1061,"author":847,"body":1062,"category":847,"cover":1121,"description":1122,"draft":850,"extension":851,"image":847,"launchCta":847,"meta":1123,"navigation":853,"ogImage":847,"path":1124,"publishedAt":1125,"readTime":847,"seo":1126,"stem":1127,"tags":1128,"updatedAt":847,"__hash__":1131},"blog\u002Fblog\u002Fminimax-is-now-available-on-monid.md","MiniMax is now available on Monid",{"type":8,"value":1063,"toc":1116},[1064,1067,1076,1080,1088,1092,1095,1097,1103,1109,1111,1114],[11,1065,1066],{"style":13},"Copy this line to your agent to create music.",[16,1068,1070],{"className":18,"code":1069,"language":20,"meta":21,"style":21},"set up https:\u002F\u002Fmonid.ai\u002FSKILL.md and create a song with MiniMax Music 2.6\n",[23,1071,1072],{"__ignoreMap":21},[26,1073,1074],{"class":28,"line":29},[26,1075,1069],{},[99,1077,1079],{"id":1078},"minimax-music-26","MiniMax Music 2.6",[11,1081,1082,1087],{},[89,1083,1086],{"href":1084,"rel":1085},"https:\u002F\u002Fwww.minimax.io",[93],"MiniMax"," Music 2.6 turns a prompt into music your agent can use right away. Describe the style, mood, lyrics, or use case, and generate a track inside the same workflow.",[99,1089,1091],{"id":1090},"minimax-text-to-image-image-01","MiniMax Text-to-Image image-01",[11,1093,1094],{},"MiniMax image-01 turns text prompts into images. Ask for a concept, scene, product visual, or creative asset, and let your agent generate it through Monid.",[99,1096,887],{"id":886},[11,1098,1099,1102],{},[89,1100,893],{"href":822,"rel":1101},[93]," is the tool layer for agents. It lets agents connect to all the tools and APIs they need, without managing signups, API keys, or subscriptions.",[11,1104,1105,1106,218],{},"Today, Monid provides tools for social media scraping, web search, image and music generation, people data search, weather APIs, ",[89,1107,901],{"href":741,"rel":1108},[93],[903,1110],{},[11,1112,1113],{},"On Monid, MiniMax becomes part of the same tool layer your agent already uses. Describe what you need, generate the image or music, and keep building.",[826,1115,977],{},{"title":21,"searchDepth":247,"depth":247,"links":1117},[1118,1119,1120],{"id":1078,"depth":247,"text":1079},{"id":1090,"depth":247,"text":1091},{"id":886,"depth":247,"text":887},"\u002Fimg\u002Fblog\u002Fminimax-is-now-available-on-monid.png","Create images and music with MiniMax models through Monid.",{},"\u002Fblog\u002Fminimax-is-now-available-on-monid","2026-06-24",{"title":1061,"description":1122},"blog\u002Fminimax-is-now-available-on-monid",[860,1057,1129,1130],"image-generation","music-generation","OYTt4aBpVNeb9nNuUTkZhyl8yzm6h4v8c8tMHC9NmFg",1784441553716]