Skip to main content

Agent pack

Research analyst agent

A research question becomes a sourced brief, with every claim carrying its source.

By
Caleb and Ryan, the founders
Updated
September 2, 2026
Version
0.1, in the library
  • Claude Code
  • Anthropic API

An agent with our research discipline built in: it plans the search, gathers from multiple sources, tags every claim with where it came from, and writes the brief with the confident and uncertain parts clearly separated. It says what it could not verify, which is most of what makes research trustworthy.

Built, documented, running.

Part of the working library we deploy from on every engagement.

Bring this into a project

Runs on

  • Claude Code
  • Anthropic API

2 requirements, below.

  • Complete and documented: the same files we run ourselves.
  • Deployed and tuned to your stack as part of an engagement.

The file

Draft excerpt
# The brief answer: the short version, sources inlineconfident: claims with two independent sourcesuncertain: one source, or sources disagreenot-found: what we looked for and could not verify

What is inside

3 items. Includes deployment guide.

  • AGENT.mdThe discipline: plan, gather, tag, separate, admit
  • brief-format.mdHow findings and uncertainty are laid out
  • guide.mdAsking questions that get good briefs back

Who it is for

  • Research means an hour of tabs and a paragraph of vibes.
  • Decisions get made on the first page of results.
  • You need sourced answers a colleague can check.

Requirements

  • An agent runtime with web access
  • Questions worth an hour of an analyst

Where this sits

  1. This system

    Research analyst agent

    In the library, running.

  2. In your stack

    Deployed on an engagement

    The audit finds which system earns its place first; we install and tune it around how you work.

Changelog

  1. September 2, 2026In the library. Version 0.1 runs in our own operation.

Related

  1. Agent pack

    Document intake and extraction

    Paperwork reads itself and files its own fields

    Works with n8n, Anthropic API.

    Built and running

  2. Agent pack

    Prospect list builder

    An ideal-customer list built on a schedule, checked against your records first

    Works with Claude Code, Anthropic API.

    Built and running

  3. Agent pack

    Objection response drafter

    Every objection your team hears gets a considered answer, kept and improved

    Works with Claude Code, Anthropic API.

    Built and running