Avido
For developers

Approved company knowledge, one call away

Give your apps and agents the same knowledge your team approved, over a REST API, an MCP server, or a folder on disk.

Answer
curl https://app.avido.dev/api/v1/answer \  -H "Authorization: Bearer $KEY" \  --json '{"question": "How long do customers have to ask for a refund?"}' # 200 OK{  "answered": true,  "answer": "Customers can ask for a full refund within 30 days [1].",  "citations": [    { "n": 1, "title": "Refund policy", "approved": true }  ]}
Build with it

What you can build on your company brain

Avido does the hard part: keeping knowledge right. You build the experience on top.

A support assistant

Answer customers from approved knowledge only, with citations anyone can check.

POST /answer

Your own RAG pipeline

Put approved passages into your own prompts, with the model you already use.

POST /search

Your own vector store

Copy passages and their embeddings into the store you run, and keep it in sync.

GET /chunks · webhooks

Assistants for your team

Connect Claude or any MCP client. Each person sees only what is shared with them.

MCP server

Coding agents that know the rules

Pull knowledge and skills into a repo on a schedule, and point Claude Code at the skills.

CLI · skills

A help center or intranet

Show approved articles on your own site, and rebuild a page when its article is published.

GET /articles · article.published
Getting started

From a key to your first answer

  1. 1Connect your sources in the app and approve what matters.
  2. 2Create an agent on the Developer page, share what it should read, and copy its key.
  3. 3Call the API, add the MCP server, or pull with the CLI.
  4. 4Subscribe to webhooks to hear when knowledge changes.
TypeScript
// Ground your own model in approved knowledgeconst res = await fetch(`${AVIDO}/api/v1/search`, {  method: "POST",  headers: {    Authorization: `Bearer ${KEY}`,    "content-type": "application/json",  },  body: JSON.stringify({ query: question, topK: 5 }),});const { data } = await res.json(); const context = data  .map((p) => `# ${p.title}\n${p.content}`)  .join("\n\n"); // Send `context` and `question` to your model.// Every passage is approved unless you ask otherwise.
Three ways in

Use it the way your stack already works

REST API

Search passages, get written answers with citations, or read whole articles and skills.

Search
# AVIDO=https://app.avido.devcurl $AVIDO/api/v1/search \  -H "Authorization: Bearer $KEY" \  --json '{"query": "refund window"}'

MCP server

Plug any MCP client into the same knowledge. Agents use a key; people sign in as themselves.

Claude Code
claude mcp add --transport http \  avido $AVIDO/mcp # Tools: search_knowledge,# get_article, list_articles,# list_skills, get_skill,# report_problem

Command line

Pull approved articles and skills into a folder as Markdown. Later pulls only change what changed.

Pull
npx avido-knowledge pull ./knowledge # knowledge/#   articles/<collection>/<slug>.md#   skills/<name>/SKILL.md
Access

Your AI only reads what it should

Approved by default

Keys read approved content only. Opt in to content that is not reviewed yet, per request.

A key per agent

Each agent gets its own key and sees only what is shared with it. Rotate or disable it any time.

A label on everything

Every article, passage, and answer says whether it is approved or not reviewed yet.

Webhooks

Hear about every change

Keep your own index, cache, or vector store in step. Deliveries are signed and retried for hours, and the same events can be read back from an ordered feed.

  • article.published
  • article.archived
  • proposal.created
  • finding.opened
  • finding.resolved
  • sharing.changed
  • sync.completed
  • index.updated
Signature
// Verify a deliveryconst expected = hmacSha256Hex(  secret,  `${headers["x-knowledge-timestamp"]}.${rawBody}`,);if (expected !== headers["x-knowledge-signature"]) reject();
Write back

Your AI helps keep the knowledge right

Nothing an app or agent sends goes live on its own. It goes to Review, where a person decides.

1

Report a problem

An agent can say an article is wrong, outdated, unclear, or missing. It lands in Review, with a fix drafted.

POST /problems
2

Send the questions that matter

Tell Avido what your AI must be able to answer. Anything not covered shows up as a gap.

POST /questions
3

Upload files

Word, PDF, Markdown, and text in. Each section becomes an article draft for review.

POST /uploads
4

Push skills

Send a SKILL.md with its files. A new version waits for a person to approve it.

POST /skills
API at a glance

One versioned API under /api/v1

Bearer keys, cursor paging, and plain JSON. The full reference, with examples in curl, JavaScript, and Python, is in the app.

Read

  • POST/searchPassages by meaning and keywords
  • POST/answerA written answer with citations
  • GET/articlesApproved articles, filtered and paged
  • GET/chunksPassages, with embeddings if you want them
  • GET/skillsApproved skills, or one as a zip

Stay in sync

  • GET/changesAn ordered feed of everything that changed
  • GET/exportThe whole library as one zip
  • POST/webhooksGet called when something changes
  • GET/activityWho published, archived, or shared what

Feed it

  • POST/uploadsFiles in, article drafts out
  • POST/sourcesAdd a website, re-read daily or weekly
  • POST/questionsQuestions your AI must answer
  • POST/problemsReport a wrong or missing article

Quality and review

  • GET/findingsContradictions, duplicates, stale content
  • POST/checksRun a check now
  • GET/review-itemsWhat is waiting, to approve or reject
For developers

Start building on your company brain

Join the waitlist to get a workspace and your first key, or book a demo and we will walk through your use case.