01 Quick start

Three steps. Sixty seconds. No code.

1

Create an agent

Go to + New agent. Give it a name (e.g. support-bot) and instructions ("answer strictly from these docs, refuse off-topic").

2

Drop your docs

Drag in PDF, Markdown, or text files. They get indexed in your private tenant. Your agent will only answer from these.

3

Ask questions

Type a question. Get back: a grounded answer, a support_score, claims with citations, and a verdict. If the docs don't cover it, the agent says so.

Why this matters: traditional chat AIs invent answers when they don't know. Studio agents only answer from your documents and show the receipts. No hallucinations on your watch.

02 How it works under the hood

Three layers run on every question.

Retrieval

Your question is embedded and matched against your indexed documents (BM25 + dense vector hybrid). The top relevant chunks are pulled into the LLM's context.

Grounded answer

The LLM is told to answer only from the retrieved chunks. If the chunks don't support an answer, it says "I don't have that information in the provided context."

Fact-checking

The answer is split into atomic claims. Each claim is verified against the source chunks. The result is a verdict:

  • SAFE — every claim is supported by your documents.
  • PARTIAL — some claims are supported, others aren't.
  • UNVERIFIED — no source context was retrieved (likely off-topic or missing docs).
  • CONFLICT — a claim contradicts your documents.

03 Agent examples

Five patterns we see working in the wild. Copy any setup as a starting point.

support · b2c & b2b

Customer support bot

Answers FAQs, billing, refunds, plans — strictly from your help center. Refuses to invent policies.

Docs: help-center.md, billing-policy.pdf Instructions: "Answer support questions using only the help center. If a customer asks about something not covered, say 'Let me get a human to confirm'."
replaces · zendesk macros, fragile chatbots
internal · onboarding

New-hire onboarding agent

Answers HR / IT / culture questions for new joiners from your handbook + setup guides.

Docs: employee-handbook.pdf, setup-laptop.md, security-101.md Instructions: "Help new hires set up. Quote section numbers when relevant. If unsure, direct them to #ask-people."
replaces · "ask in slack" loops
sales · pre-purchase

Pricing & product Q&A

Pre-sales agent that answers prospects from your pricing page, comparison docs, security PDFs.

Docs: pricing.md, security-whitepaper.pdf, feature-comparison.md Instructions: "Answer enterprise prospects. Be specific on tier limits. For deals above $X/yr, suggest booking a call."
replaces · long demo cycles
compliance · regulated

Compliance & legal helper

Answers strictly from policy / regulation docs. Hallucinations here = liability.

Docs: gdpr-internal-policy.pdf, soc2-controls.md, data-retention.md Instructions: "Quote source paragraphs verbatim. If a question goes beyond the documents, decline and route to legal@."
replaces · email-the-lawyer ticket queue
ops · technical

Runbook / SOP agent

On-call helper. Answers "how do I rotate the X key?" / "what's the rollback playbook?" from your runbooks.

Docs: runbooks/*.md, postmortems/*.md Instructions: "Surface the exact command and section. If the runbook conflicts with itself, flag both versions."
replaces · grep-through-confluence at 3am
research · personal

Personal research agent

Project-scoped agent on top of papers, transcripts, notes. Lets you ask "where did I read X?" with citations.

Docs: papers/*.pdf, meeting-notes/*.md Instructions: "Be exhaustive. Quote 1-2 sentences from each source. Mark any conflict between papers explicitly."
replaces · obsidian search + memory

04 What your agent can & can't do

Studio agents are RAG-grounded by design. No external tools, no web access — just your docs and a verified answer.

Can doCan't do (yet)
Answer from your docs with grounded citations Browse the web in real time
Refuse off-topic questions when given the right system prompt Run code or call external APIs
Quote source paragraphs verbatim with file + section Update its own knowledge base — re-upload to refresh
Fact-check itself claim by claim, with a verdict Send emails, post to Slack, hit your DB
Detect contradictions between your own docs Remember past conversations across runs (each run is independent)
Refuse to invent when the docs don't cover a question Ingest images / video — text only for now
Need tools (web, SQL, Slack, email)? The full Wauldo platform exposes ~30 tools via the Agents API. See the full list and example agents →

05 Limits

ResourceTrialPro · $29/mo
Agents25
Runs (rolling 24h / 30d)10 / day500 / month
Document upload10 MB total100 MB total
Per-file size10 MB10 MB
Verification (SAFE / PARTIAL / UNVERIFIED / CONFLICT)✓ included✓ included
Source citations on every answer✓ included✓ included
Stats & verdict distribution dashboard✓ after 5 runs✓ included
Email supportcontact@wauldo.com

Beyond Pro, the same engine is exposed via the Wauldo Agents API with a 30-tool runtime, parallel workflows, and per-tenant rate limits.

06 Tips for great agents

Write the system prompt like a job description

Be explicit about scope, tone, refusals. Bad: "answer questions". Good: "answer billing questions strictly from billing.pdf. Quote section numbers. Refuse anything outside billing — route to a human."

Curate your docs hard

Three clean, current PDFs beat thirty stale ones. Outdated docs = wrong answers (with high confidence). Re-upload after every policy change.

Test with adversarial questions

After deploy, run 5–10 prompts you know the answer to. Then 2–3 you know are not covered. Verify the agent refuses cleanly on the second batch — that's where trust is earned.

Read the verdict, not just the answer

SAFE 0.95 + 5/5 claims supported = trust the answer. PARTIAL 0.6 + 2/5 supported = read the answer carefully. CONFLICT = your docs disagree with each other; fix them, not the agent.

Use one agent per use case

Don't pile customer-support docs and engineering runbooks into the same agent. The retrieval gets fuzzy. Two focused agents beat one overloaded one.

07 Tools (Agents API)

Studio agents are RAG-only. The full Wauldo Agents API gives your agent a 30-tool runtime: web search, SQL, Slack, email, GitHub, scheduler, file system. Ship it via /v1/agents when chat-with-docs isn't enough.

Compute & data

calculatornative
datetimenative
sql_querynative
analytics_fetchernative
pricing_managernative
routernative

File & storage

file_operationsnative
mcp_fs_readmcp · 14 ops
rag_retrievenative

Research & web

web_searchtavily key
wikipedianative
arxivnative
rss_feednative

Communication & automation

slack_webhooknative
email_smtpsmtp creds
social_posternative
schedulernative

Integrations

githubgithub token

Dashed pills = env-gated (need an API key). The MCP bridge auto-registers any external server's tools (filesystem, memory, brave, …) via MCP_CONFIG_PATH.

Example agents that combine tools

Each row below is a real agent shape — a system prompt + a tool whitelist. The Agents API runs the workflow, retries on failure, and verifies every claim.

📰 Daily news digest agent

Reads your industry RSS feeds every morning, enriches each headline with a 1-line web search summary, posts the digest to a Slack channel.

rss_feedweb_searchslack_webhookscheduler
scheduler → triggers daily 08:00 UTC rss_feed → pulls 5 feeds, returns top 10 headlines web_search → 1-line summary per headline (Tavily) slack_webhook → formatted digest to #ai-news
🔬 Research assistant

"Find recent papers on X, cross-reference with my notes, email me a summary with citations."

arxivwikipediarag_retrieveemail_smtp
arxiv → top 10 recent papers on the topic wikipedia → context lookup on terms rag_retrieve → match against your indexed notes email_smtp → markdown summary with arxiv links
⚙️ GitHub PR triage agent

Watches a repo's open PRs, queries your CI metrics DB for risk flags, posts a "needs review" digest to engineering Slack.

githubsql_queryslack_webhookscheduler
scheduler → twice-daily (10:00, 17:00) github → list open PRs older than 24h sql_query → flag risky PRs (touching critical paths) slack_webhook → ranked PR list with @mentions
📊 Sales analytics agent

"Weekly recap: top 5 plans, MRR delta, churn warnings — emailed to founders Monday 9am."

sql_queryanalytics_fetcherpricing_manageremail_smtpscheduler
scheduler → Monday 09:00 UTC sql_query → per-plan revenue + count analytics_fetcher → PostHog signups + retention pricing_manager → MRR / ARPU / churn calc email_smtp → markdown report to founders@
🛡️ Compliance watchdog

Indexes your policy docs, monitors Slack for risky language, alerts compliance team with the policy section that was potentially crossed.

rag_retrieveslack_webhookscheduler
scheduler → polls Slack every 15min rag_retrieve → match recent messages vs policies slack_webhook → DM compliance lead with citation if rule potentially crossed
Want one of these? Today they're built via the Wauldo Agents API (one HTTP call to define the workflow). Studio's no-code builder ships these patterns in the next phase — drop your email at contact@wauldo.com and tell us which recipe you want first.

08 FAQ

Click to expand.

Are my documents private?

Yes. Each Studio account is a tenant. Your docs are indexed in a tenant-scoped knowledge base — no other Studio user can retrieve them. Documents are not used to train any model.

What models does Studio use?

Studio routes through the Wauldo backend, which uses Qwen / Claude / GPT depending on the question complexity (auto-selected for cost-quality balance). All inference is server-side; the user-facing experience is consistent.

What file types are supported?

PDF, Markdown (.md), plain text (.txt). Up to 10 MB per file. PDFs are extracted to text — formatting (tables, images) may be lost.

Why did my answer come back UNVERIFIED?

Either no source context was retrieved (the docs don't cover that question), or the docs aren't indexed yet (rare — usually a transient backend issue). Try rephrasing closer to the language used in your docs.

Why did my answer come back CONFLICT?

The fact-checker found a claim that contradicts what's in your retrieved chunks. Often this means your docs disagree with each other (a v1 and v2 of the same policy both indexed). Audit the cited sources and clean up.

Can I delete an agent or my account?

Delete an agent: hit "Delete" on the agents page. Delete your whole account / data: email contact@wauldo.com — full GDPR export & delete on request.