{ }
A CrewAI-style research desk with role-based agents for source discovery, analysis, critique, and publishing, built for briefs that need evidence instead of vibes.
Designed for
Founders, product marketers, and AI startups that need repeatable market, customer, and competitor research workflows
Operating goal
Turn messy research questions into sourced briefs with a visible claim ledger and a critic agent that rejects weak evidence.
4 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.
Finds primary sources and records capture context.
Fast research model
Turns sources into claims and implications.
Reasoning model
Rejects weak claims and flags unsupported leaps.
Critical review model
Writes the final brief and stakeholder summary.
High-quality writing model
Loads the workflow goal, allowed actions, escalation policy, and output contract before the agent plans work.
A workflow skill that captures the operating contract, tool boundaries, and escalation rules for CrewAI — Multi-Agent Research Desk.
Centralizes high-risk action checks for writes, secrets, customer data, billing, deploys, and public communications.
Exposes task resources, prompt templates, connector tools, and audit records behind a permission-aware boundary.
Find public and internal sources with capture dates.
Cluster sources into claims, implications, and open questions.
Reject unsupported claims and request revisions.
Write final brief, source ledger, and stakeholder summary.
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 Slack-native engineering agent that receives operational requests, gathers context from tickets and repos, routes work to specialist agents, and drafts auditable responses before anything risky happens.
A 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 guarded browser operator for internal tools: it can open approved apps, complete repetitive workflows, verify the result, and stop at human approval checkpoints before sensitive writes.