[{"data":1,"prerenderedAt":888},["ShallowReactive",2],{"blog-\u002Fblog\u002Flive-web-search-your-agent-can-call":3,"blog-related-\u002Fblog\u002Flive-web-search-your-agent-can-call":617},{"id":4,"title":5,"author":6,"body":7,"category":600,"cover":601,"description":602,"draft":603,"extension":604,"image":600,"launchCta":600,"meta":605,"navigation":606,"ogImage":600,"path":607,"publishedAt":608,"readTime":600,"seo":609,"stem":610,"tags":611,"updatedAt":600,"__hash__":616},"blogUnlisted\u002Fblog\u002Flive-web-search-your-agent-can-call.md","Live Web Search Your Agent Can Actually Call","The Monid Team",{"type":8,"value":9,"toc":583},"minimark",[10,15,85,104,109,134,138,141,146,149,152,156,159,185,192,196,199,208,212,219,223,227,236,243,252,256,313,321,325,343,439,503,507,522,526,532,544,550,561,565,579],[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 at runtime.",[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 \u002Fsearch to fetch fresh web results and contents inside your agent loop\n","sh","",[23,24,25],"code",{"__ignoreMap":21},[26,27,30,34,38,41,44,47,50,53,56,59,62,65,68,70,73,76,79,82],"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}," \u002Fsearch",[26,54,55],{"class":36}," to",[26,57,58],{"class":36}," fetch",[26,60,61],{"class":36}," fresh",[26,63,64],{"class":36}," web",[26,66,67],{"class":36}," results",[26,69,43],{"class":36},[26,71,72],{"class":36}," contents",[26,74,75],{"class":36}," inside",[26,77,78],{"class":36}," your",[26,80,81],{"class":36}," agent",[26,83,84],{"class":36}," loop\n",[11,86,87,88,95,96,103],{},"An agent should fetch the web when it is answering, not weeks earlier when someone built its index. We ship live web search as a single runtime call: ",[89,90,94],"a",{"href":91,"rel":92},"https:\u002F\u002Fexa.ai",[93],"nofollow","Exa","'s ",[89,97,100],{"href":98,"rel":99},"https:\u002F\u002Fexa.ai\u002Fdocs\u002Freference\u002Fsearch",[93],[23,101,102],{},"\u002Fsearch"," endpoint on Monid returns ranked results and the extracted page contents in the same response, so the agent reads fresh sources the moment it needs them and skips the separate fetch-and-parse step entirely. Monid is a pay-per-call data API marketplace: one integration and one wallet reach hundreds of external data endpoints across web search, scraping, enrichment, social data, and generative media, without a separate signup per vendor. This post is about why we put web search behind that same interface, and the few principles that make it work for an agent rather than a nightly batch job.",[105,106,108],"h2",{"id":107},"tldr","TL;DR",[110,111,112,120,128,131],"ul",{},[113,114,115,116,119],"li",{},"A pre-built vector index answers questions about the past. An agent answering questions about right now needs a call it can make mid-reasoning, which is what ",[23,117,118],{},"exa \u002Fsearch"," is.",[113,121,122,123,127],{},"One call returns ranked results ",[124,125,126],"strong",{},"and"," the cleaned page text together, so there is no second scrape-and-parse hop to wire, retry, or pay for separately.",[113,129,130],{},"Web search lives in the same catalog and the same wallet as every other data endpoint, so adding it does not mean a new key, a new invoice, or a new client library.",[113,132,133],{},"Because Monid ships as an MCP server, the agent discovers and routes this call itself. You do not hand-code the tool call; the model picks it when the question calls for it.",[105,135,137],{"id":136},"four-principles-behind-agent-callable-web-search","Four principles behind agent-callable web search",[11,139,140],{},"We designed this around four ideas. Naming them makes it clear what a runtime web-search tool has to get right.",[142,143,145],"h3",{"id":144},"_1-runtime-not-build-time","1. Runtime, not build-time",[11,147,148],{},"Most \"give your agent the web\" setups are actually build-time: a crawler runs on a schedule, an embedding job turns pages into vectors, and the agent retrieves from that frozen snapshot. That is a fine design for a corpus that does not move, like your own documentation. It is the wrong design for questions about this morning. The index is only ever as fresh as its last crawl, the crawl costs compute whether or not anyone asks about those pages, and a breaking story from an hour ago simply is not in there.",[11,150,151],{},"Runtime search inverts that. The agent decides, in the middle of reasoning, that it lacks a fact, and it fetches at that instant. Nothing is pre-indexed, nothing goes stale, and you pay for the search you actually needed rather than a standing crawl of pages nobody queried. The tradeoff is latency on the request itself, which is exactly the tradeoff you want when correctness depends on freshness.",[142,153,155],{"id":154},"_2-results-plus-contents-in-one-call","2. Results plus contents in one call",[11,157,158],{},"The reason web search is usually two vendors is that retrieval and reading are usually two jobs. A search API hands back a ranked list of URLs. Then something has to open each URL, strip the navigation and ads, and return clean body text a model can hold in its context. Teams bolt a scraping or extraction service onto the search API to do that second half, and inherit two failure modes, two rate limits, and a pile of glue.",[11,160,161,162,164,165,168,169,172,173,176,177,180,181,184],{},"Exa's ",[23,163,102],{}," folds both halves into one request. Set the ",[23,166,167],{},"contents"," field and the response carries, per result, the cleaned ",[23,170,171],{},"text"," (with an optional ",[23,174,175],{},"maxCharacters"," cap), ",[23,178,179],{},"highlights"," (the sentences most relevant to a sub-query), and a per-source ",[23,182,183],{},"summary",". The agent never sees raw HTML and never calls a second service. One request, one charged unit, results and readable contents arriving together.",[11,186,187],{},[188,189],"img",{"alt":190,"src":191},"An agent spots a gap in what it knows, makes one exa \u002Fsearch call through monid that returns fresh ranked results and extracted page text together, produces a grounded answer, and loops back for a follow-up query when it needs more","\u002Fimg\u002Fblog\u002Flive-web-search-your-agent-can-call-fig-exap-1.png",[142,193,195],{"id":194},"_3-one-wallet-across-every-data-endpoint","3. One wallet across every data endpoint",[11,197,198],{},"An agent rarely needs only search. The same session might enrich a company, pull a few social posts, or generate an image. If each of those is a separate vendor, you are managing a drawer of API keys, reconciling a stack of invoices, and teaching your agent a different client for each. We think that is the actual tax on building capable agents, and it is the tax Monid removes.",[11,200,201,202,207],{},"Web search sits in the same catalog as company enrichment, LinkedIn scraping, and the rest, priced the same pay-as-you-go way and drawn from the same wallet. Adding live search to an agent that already talks to Monid is not a new integration. It is one more endpoint the agent can already reach. Current per-endpoint pricing is at ",[89,203,206],{"href":204,"rel":205},"https:\u002F\u002Fmonid.ai\u002Ftools",[93],"monid.ai\u002Ftools",", and because inspecting an endpoint is free, the agent can read the price before it ever spends.",[142,209,211],{"id":210},"_4-mcp-native-so-the-agent-routes-it-itself","4. MCP-native, so the agent routes it itself",[11,213,214,215,218],{},"Because Monid ships as an MCP server, the agent does not get a hardcoded ",[23,216,217],{},"search()"," tool you wrote. It gets the whole catalog as callable capability and picks the right endpoint for the question in front of it. When it hits something outside its training window, it can discover the search endpoint, inspect the schema, and make the call on its own, all inside its normal loop. Discover and inspect are free; only the run bills. That is the one sentence of mechanism worth stating, because it is what turns \"web search\" from a tool you plumb into a decision the model makes.",[105,220,222],{"id":221},"set-up-once","Set up once",[142,224,226],{"id":225},"for-agents","For agents",[11,228,229,230,235],{},"Grab an API key at ",[89,231,234],{"href":232,"rel":233},"https:\u002F\u002Fapp.monid.ai\u002F",[93],"app.monid.ai",", then paste this to your agent and hand it the key:",[16,237,241],{"className":238,"code":240,"language":171},[239],"language-text","set up https:\u002F\u002Fmonid.ai\u002FSKILL.md\n",[23,242,240],{"__ignoreMap":21},[11,244,245,246,251],{},"It learns the whole discover, inspect, run workflow itself. More details in the ",[89,247,250],{"href":248,"rel":249},"https:\u002F\u002Fmonid.ai\u002Fdocs\u002Fguide\u002Fquickstart-skill",[93],"agent quickstart",".",[142,253,255],{"id":254},"for-humans","For humans",[16,257,261],{"className":258,"code":259,"language":260,"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",[23,262,263,278],{"__ignoreMap":21},[26,264,265,269,272,275],{"class":28,"line":29},[26,266,268],{"class":267},"sBMFI","npm",[26,270,271],{"class":36}," install",[26,273,274],{"class":36}," -g",[26,276,277],{"class":36}," @monid-ai\u002Fcli\n",[26,279,281,284,287,290,293,296,299,303,306,310],{"class":28,"line":280},2,[26,282,283],{"class":267},"monid",[26,285,286],{"class":36}," keys",[26,288,289],{"class":36}," add",[26,291,292],{"class":36}," --label",[26,294,295],{"class":36}," main",[26,297,298],{"class":36}," --key",[26,300,302],{"class":301},"sMK4o"," \u003C",[26,304,305],{"class":36},"your-api-ke",[26,307,309],{"class":308},"sTEyZ","y",[26,311,312],{"class":301},">\n",[11,314,315,316,251],{},"More details in the ",[89,317,320],{"href":318,"rel":319},"https:\u002F\u002Fmonid.ai\u002Fdocs\u002Fguide\u002Fquickstart-cli",[93],"CLI quickstart",[105,322,324],{"id":323},"the-one-call-end-to-end","The one call, end to end",[11,326,327,328,331,332,335,336,339,340,342],{},"Here is the whole runtime step. Pass the agent's question as ",[23,329,330],{},"query",", keep ",[23,333,334],{},"numResults"," small because a few strong sources beat a wall of text, bound the window with ",[23,337,338],{},"startPublishedDate"," for anything time-sensitive, and set ",[23,341,167],{}," so the response arrives already readable.",[16,344,346],{"className":258,"code":345,"language":260,"meta":21,"style":21},"monid run -p exa -e \u002Fsearch \\\n  -i '{\"query\": \"latest EU AI Act enforcement guidance\",\n       \"type\": \"neural\",\n       \"category\": \"news\",\n       \"numResults\": 5,\n       \"startPublishedDate\": \"2026-07-01T00:00:00Z\",\n       \"contents\": {\"text\": {\"maxCharacters\": 1200},\n                    \"highlights\": {\"query\": \"enforcement changes\", \"numSentences\": 2}}}' \\\n  -w\n# -> five recent sources, each with up to 1200 chars of clean body text\n#    and the two most relevant sentences, plus a costDollars breakdown\n",[23,347,348,368,379,385,391,397,403,409,420,426,433],{"__ignoreMap":21},[26,349,350,352,355,358,360,363,365],{"class":28,"line":29},[26,351,283],{"class":267},[26,353,354],{"class":36}," run",[26,356,357],{"class":36}," -p",[26,359,49],{"class":36},[26,361,362],{"class":36}," -e",[26,364,52],{"class":36},[26,366,367],{"class":308}," \\\n",[26,369,370,373,376],{"class":28,"line":280},[26,371,372],{"class":36},"  -i",[26,374,375],{"class":301}," '",[26,377,378],{"class":36},"{\"query\": \"latest EU AI Act enforcement guidance\",\n",[26,380,382],{"class":28,"line":381},3,[26,383,384],{"class":36},"       \"type\": \"neural\",\n",[26,386,388],{"class":28,"line":387},4,[26,389,390],{"class":36},"       \"category\": \"news\",\n",[26,392,394],{"class":28,"line":393},5,[26,395,396],{"class":36},"       \"numResults\": 5,\n",[26,398,400],{"class":28,"line":399},6,[26,401,402],{"class":36},"       \"startPublishedDate\": \"2026-07-01T00:00:00Z\",\n",[26,404,406],{"class":28,"line":405},7,[26,407,408],{"class":36},"       \"contents\": {\"text\": {\"maxCharacters\": 1200},\n",[26,410,412,415,418],{"class":28,"line":411},8,[26,413,414],{"class":36},"                    \"highlights\": {\"query\": \"enforcement changes\", \"numSentences\": 2}}}",[26,416,417],{"class":301},"'",[26,419,367],{"class":308},[26,421,423],{"class":28,"line":422},9,[26,424,425],{"class":36},"  -w\n",[26,427,429],{"class":28,"line":428},10,[26,430,432],{"class":431},"sHwdD","# -> five recent sources, each with up to 1200 chars of clean body text\n",[26,434,436],{"class":28,"line":435},11,[26,437,438],{"class":431},"#    and the two most relevant sentences, plus a costDollars breakdown\n",[11,440,441,442,445,446,449,450,453,454,457,458,461,462,465,466,469,470,473,474,461,477,461,480,461,483,486,487,490,491,494,495,498,499,502],{},"The ",[23,443,444],{},"-w"," flag waits inline so the agent gets everything in one shot. The fields that shape a good research step are ",[23,447,448],{},"type"," (from ",[23,451,452],{},"instant"," and ",[23,455,456],{},"fast"," up through ",[23,459,460],{},"neural",", ",[23,463,464],{},"deep",", and ",[23,467,468],{},"deep-reasoning","), ",[23,471,472],{},"category"," (narrow to ",[23,475,476],{},"news",[23,478,479],{},"research paper",[23,481,482],{},"company",[23,484,485],{},"financial report",", and more), the date bounds, and ",[23,488,489],{},"includeDomains"," or ",[23,492,493],{},"excludeDomains"," to trust or drop sources. There is also ",[23,496,497],{},"outputSchema",", which asks Exa to synthesize one structured JSON object across every source it read, so your code gets a filled-in answer instead of a pile of pages. Every one of these is visible from a free ",[23,500,501],{},"monid inspect -p exa -e \u002Fsearch"," before you spend a cent.",[105,504,506],{"id":505},"what-live-search-actually-costs","What live search actually costs",[11,508,509,510,512,513,515,516,518,519,251],{},"Because ",[23,511,102],{}," bills per call rather than per token or per page, the cost of one research step is a flat unit you know before you run it. Asking for five results or fifty is still one charged call, and setting ",[23,514,167],{}," does not add a second charge because there is no second service. An agent that fires a handful of search calls per session sits in fractions of a cent to a few cents per session, and a tool running those all day lands in single-digit dollars. Compare that to a standing crawl-and-embed pipeline, where you pay compute continuously to keep an index warm whether or not anyone queries it. Reach for a ",[23,517,464],{}," search mode when a question is genuinely hard, keep it lean when it is not, and the bill tracks the work. Live prices are at ",[89,520,206],{"href":204,"rel":521},[93],[105,523,525],{"id":524},"faq","FAQ",[11,527,528,531],{},[124,529,530],{},"Why not just build a vector index of the web?","\nAn index answers from whenever it was last crawled, which is the wrong tense for questions about now. Runtime search fetches at the moment the agent asks, so freshness is guaranteed and you never pay to keep pages warm that nobody queries.",[11,533,534,537,538,540,541,543],{},[124,535,536],{},"How does one call do both search and extraction?","\nExa's ",[23,539,102],{}," takes a ",[23,542,167],{}," object alongside the query. Set it and each result comes back with the cleaned page text, highlights, or a summary, so retrieval and reading happen in the same request instead of across two vendors.",[11,545,546,549],{},[124,547,548],{},"Do I need a separate Exa key and a scraper?","\nNo. You integrate Monid once and fund one pay-as-you-go wallet, and that wallet reaches Exa's search-and-extract endpoint alongside every other data endpoint in the catalog. No second key for parsing, no second invoice.",[11,551,552,555,556,251],{},[124,553,554],{},"Can the agent decide to call this on its own?","\nYes. Monid ships as an MCP server, so an agent that hits a question it cannot answer from memory can discover the endpoint, inspect the schema for free, and make the call itself. See ",[89,557,560],{"href":558,"rel":559},"https:\u002F\u002Fmonid.ai\u002FSKILL.md",[93],"monid.ai\u002FSKILL.md",[105,562,564],{"id":563},"try-it","Try it",[11,566,567,568,570,571,573,574,251],{},"Point your agent at Monid, hand it a question you know the answer to, and let it call ",[23,569,118],{}," with ",[23,572,167],{}," set. If the extracted text matches what you would find opening the pages yourself, wrap it as the agent's live-search step and let the model reach for it whenever its training runs out. Start at ",[89,575,578],{"href":576,"rel":577},"https:\u002F\u002Fmonid.ai",[93],"monid.ai",[580,581,582],"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":280,"depth":280,"links":584},[585,586,592,596,597,598,599],{"id":107,"depth":280,"text":108},{"id":136,"depth":280,"text":137,"children":587},[588,589,590,591],{"id":144,"depth":381,"text":145},{"id":154,"depth":381,"text":155},{"id":194,"depth":381,"text":195},{"id":210,"depth":381,"text":211},{"id":221,"depth":280,"text":222,"children":593},[594,595],{"id":225,"depth":381,"text":226},{"id":254,"depth":381,"text":255},{"id":323,"depth":280,"text":324},{"id":505,"depth":280,"text":506},{"id":524,"depth":280,"text":525},{"id":563,"depth":280,"text":564},null,"\u002Fimg\u002Fblog\u002Flive-web-search-your-agent-can-call.png","Give your AI agent live web search at runtime: one Exa \u002Fsearch call on Monid returns ranked results and page contents together, from one wallet.",false,"md",{},true,"\u002Fblog\u002Flive-web-search-your-agent-can-call","2026-07-14",{"title":5,"description":602},"blog\u002Flive-web-search-your-agent-can-call",[612,613,614,615],"ai agents","web search","exa","mcp","pWYAONNtQhmBJk2rq2pUNnU3KgSvnRYfaeZbUuorZP0",[618,681,749,815],{"id":619,"title":620,"author":600,"body":621,"category":600,"cover":666,"description":21,"draft":603,"extension":604,"image":600,"launchCta":667,"meta":670,"navigation":606,"ogImage":600,"path":671,"publishedAt":672,"readTime":600,"seo":673,"stem":674,"tags":675,"updatedAt":600,"__hash__":680},"blog\u002Fblog\u002Fakta-pro-is-now-available-on-monid.md","Introducing private markets\ndata for agents",{"type":8,"value":622,"toc":662},[623,627,635,638,642,649,656,659],[105,624,626],{"id":625},"what-is-aktapro","What is akta.pro",[11,628,629,634],{},[89,630,633],{"href":631,"rel":632},"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.",[11,636,637],{},"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.",[105,639,641],{"id":640},"what-is-monid","What is Monid",[11,643,644,648],{},[89,645,647],{"href":576,"rel":646},[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.",[11,650,651,652,251],{},"Today, Monid provides tools for social media scraping, web search, image and\nmusic generation, people data search, weather APIs, ",[89,653,655],{"href":204,"rel":654},[93],"and more",[657,658],"hr",{},[11,660,661],{},"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":280,"depth":280,"links":663},[664,665],{"id":625,"depth":280,"text":626},{"id":640,"depth":280,"text":641},"\u002Fimg\u002Fblog\u002Fakta-pro-is-now-available-on-monid-v2.png",{"label":668,"command":669},"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":620,"description":21},"blog\u002Fakta-pro-is-now-available-on-monid",[676,677,678,679],"agents","partner-tools","private-markets","data","yZnqIVof0gIpw9VH6HcE3rzit5OdTvPyC6k--T1kYa8",{"id":682,"title":683,"author":600,"body":684,"category":600,"cover":738,"description":739,"draft":603,"extension":604,"image":600,"launchCta":600,"meta":740,"navigation":606,"ogImage":600,"path":741,"publishedAt":742,"readTime":600,"seo":743,"stem":744,"tags":745,"updatedAt":600,"__hash__":748},"blog\u002Fblog\u002Fyour-claude-code-can-now-make-phone-calls.md","Your Claude Code can now make phone calls",{"type":8,"value":685,"toc":734},[686,689,698,702,710,713,715,720,726,728,731],[11,687,688],{"style":13},"Copy this line to your agent to make your first phone call.",[16,690,692],{"className":18,"code":691,"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",[23,693,694],{"__ignoreMap":21},[26,695,696],{"class":28,"line":29},[26,697,691],{},[105,699,701],{"id":700},"what-is-saperly","What is Saperly",[11,703,704,709],{},[89,705,708],{"href":706,"rel":707},"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.",[11,711,712],{},"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.",[105,714,641],{"id":640},[11,716,717,648],{},[89,718,647],{"href":576,"rel":719},[93],[11,721,722,723,251],{},"Today, Monid provides tools for social media scraping, web search, image \u002F\nmusic \u002F 3d model generation, people data search, weather APIs, ",[89,724,655],{"href":204,"rel":725},[93],[657,727],{},[11,729,730],{},"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.",[580,732,733],{},"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":280,"depth":280,"links":735},[736,737],{"id":700,"depth":280,"text":701},{"id":640,"depth":280,"text":641},"\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":683,"description":739},"blog\u002Fyour-claude-code-can-now-make-phone-calls",[676,677,746,747],"voice","phone","X0vLpqb1Vn9mIFY4XAQ16a67_nbOfiZV8NEdV12nu1A",{"id":750,"title":751,"author":600,"body":752,"category":600,"cover":804,"description":805,"draft":603,"extension":604,"image":600,"launchCta":600,"meta":806,"navigation":606,"ogImage":600,"path":807,"publishedAt":808,"readTime":600,"seo":809,"stem":810,"tags":811,"updatedAt":600,"__hash__":814},"blog\u002Fblog\u002Fintroducing-suzanne-chatgpt-for-3d-models.md","Introducing\nClaude for 3D models",{"type":8,"value":753,"toc":800},[754,757,766,770,778,781,783,788,793,795,798],[11,755,756],{"style":13},"Copy this line to your agent to generate your 3D model.",[16,758,760],{"className":18,"code":759,"language":20,"meta":21,"style":21},"set up https:\u002F\u002Fmonid.ai\u002FSKILL.md and create a 3D model for a rabbit\n",[23,761,762],{"__ignoreMap":21},[26,763,764],{"class":28,"line":29},[26,765,759],{},[105,767,769],{"id":768},"what-is-suzanne","What is Suzanne",[11,771,772,777],{},[89,773,776],{"href":774,"rel":775},"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.",[11,779,780],{},"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.",[105,782,641],{"id":640},[11,784,785,648],{},[89,786,647],{"href":576,"rel":787},[93],[11,789,651,790,251],{},[89,791,655],{"href":204,"rel":792},[93],[657,794],{},[11,796,797],{},"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.",[580,799,733],{},{"title":21,"searchDepth":280,"depth":280,"links":801},[802,803],{"id":768,"depth":280,"text":769},{"id":640,"depth":280,"text":641},"\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":751,"description":805},"blog\u002Fintroducing-suzanne-chatgpt-for-3d-models",[812,676,813],"3d","creative-tools","_S0uHM_dNVZKt_1ohYV4hn2Fm6SMxsDxzSezZf6lYFQ",{"id":816,"title":817,"author":600,"body":818,"category":600,"cover":877,"description":878,"draft":603,"extension":604,"image":600,"launchCta":600,"meta":879,"navigation":606,"ogImage":600,"path":880,"publishedAt":881,"readTime":600,"seo":882,"stem":883,"tags":884,"updatedAt":600,"__hash__":887},"blog\u002Fblog\u002Fminimax-is-now-available-on-monid.md","MiniMax is now available on Monid",{"type":8,"value":819,"toc":872},[820,823,832,836,844,848,851,853,859,865,867,870],[11,821,822],{"style":13},"Copy this line to your agent to create music.",[16,824,826],{"className":18,"code":825,"language":20,"meta":21,"style":21},"set up https:\u002F\u002Fmonid.ai\u002FSKILL.md and create a song with MiniMax Music 2.6\n",[23,827,828],{"__ignoreMap":21},[26,829,830],{"class":28,"line":29},[26,831,825],{},[105,833,835],{"id":834},"minimax-music-26","MiniMax Music 2.6",[11,837,838,843],{},[89,839,842],{"href":840,"rel":841},"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.",[105,845,847],{"id":846},"minimax-text-to-image-image-01","MiniMax Text-to-Image image-01",[11,849,850],{},"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.",[105,852,641],{"id":640},[11,854,855,858],{},[89,856,647],{"href":576,"rel":857},[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.",[11,860,861,862,251],{},"Today, Monid provides tools for social media scraping, web search, image and music generation, people data search, weather APIs, ",[89,863,655],{"href":204,"rel":864},[93],[657,866],{},[11,868,869],{},"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.",[580,871,733],{},{"title":21,"searchDepth":280,"depth":280,"links":873},[874,875,876],{"id":834,"depth":280,"text":835},{"id":846,"depth":280,"text":847},{"id":640,"depth":280,"text":641},"\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":817,"description":878},"blog\u002Fminimax-is-now-available-on-monid",[676,813,885,886],"image-generation","music-generation","OYTt4aBpVNeb9nNuUTkZhyl8yzm6h4v8c8tMHC9NmFg",1784441553875]