A research workflow that gathers competitor signals, checks source quality, extracts positioning patterns, and writes briefs that separate facts from interpretation.
Designed for
Founders, product marketers, and AI startup teams exploring markets, competitors, and customer segments
Operating goal
Produce sourced research briefs with reusable evidence packs instead of unsourced strategy guesses.
3 steps from trigger to verified handoff, with success and failure paths.
1 MCP layer and 4 connected tools with explicit auth and risk levels.
3 guardrails, 3 evals, and 1 harnesses before production use.
Turns vague research requests into precise questions.
Fast reasoning model
Collects public evidence and records source quality.
Long-context model
Turns evidence into a practical product or GTM brief.
High-quality writing model
Loads the workflow goal, allowed actions, escalation policy, and output contract before the agent plans work.
A research skill that turns public evidence into a brief with source ledger, confidence labels, and next questions.
Centralizes high-risk action checks for writes, secrets, customer data, billing, deploys, and public communications.
Exposes public-source search, source ledger resources, brief templates, and citation checks.
Clarify audience, market, competitors, and decision needed.
Gather public sources and extract claims into the ledger.
Produce a concise sourced brief with opportunities and risks.
Open it in Codelit, refine it with the agent chat, then generate the architecture or product board from the same workflow spec.
Open in Agent WorkflowA controlled workflow for small teams that want an internal agent to answer operational questions, create tickets, inspect connected apps, and prepare approved actions across the company stack.
A support workflow that reads product docs, checks account and billing state, drafts empathetic replies, and escalates sensitive requests with source-linked evidence.
A finance-aware workflow that inspects subscriptions, invoices, usage limits, and customer requests, then drafts revenue-safe actions for approval.