Competitor research brief: Multi-Step Agent Workflow for Claude Code, Codex or ChatGPT

A lead agent plans the research, sends one subagent per competitor, then writes a one-page brief with sources.

Prompt

Installs to .agents/skills/competitor-research-brief-multi-step-agent-workflow-for-claude-c/

mkdir -p .agents/skills/competitor-research-brief-multi-step-agent-workflow-for-claude-c && curl -sL "https://prompts-gpt.com/prompts/competitor-research-brief-multi-step-agent-workflow-for-claude-code-codex-or-chatgpt/raw" -o .agents/skills/competitor-research-brief-multi-step-agent-workflow-for-claude-c/SKILL.md
SKILL.md
Preview
---
name: competitor-research-brief-multi-step-agent-workflow-for-claude-c
description: "A lead agent plans the research, sends one subagent per competitor, then writes a one-page brief with sources."
---

# Competitor research brief: Multi-Step Agent Workflow for Claude Code, Codex or ChatGPT

A lead agent plans the research, sends one subagent per competitor, then writes a one-page brief with sources.

## Prompt

```
---
name: competitor-research-brief
description: A lead agent plans the research, sends one subagent per competitor, then writes a one-page brief with sources. Use when asked to run the "Competitor research brief" workflow.
---

# Competitor research brief

A lead agent plans the research, sends one subagent per competitor, then writes a one-page brief with sources.

## Inputs

Ask for any of these that the user hasn't given:

- `company` (e.g. "Prompts-GPT.com")
- `competitors` (e.g. "PromptBase, FlowGPT, PromptHero")

## Steps

Run the steps in order. Refer to saved results by name. Don't skip a step that says STOP.

1. **Manual start** — Start: Start with `company` and `competitors`.
2. **Plan the research** — List the 5 questions that matter for `company`: pricing, audience, top content, traffic sources, gaps. Save the result as `plan`.
3. **One subagent per competitor** — Launch these as parallel subagents in one message, then wait for all of them. For each name in `competitors`, answer `plan` with a source URL for every claim. Save the result as `notes`.
   - **Competitor 1**: Answer the plan for the first competitor.
   - **Competitor 2**: Answer the plan for the second competitor.
   - **Competitor 3**: Answer the plan for the third competitor.
4. **Write the brief** — Turn `notes` into a one-page brief: a comparison table, 3 openings for `company`, and sources. Save the result as `brief`.
5. **Save the brief** — Finish: Save `brief` to research/competitors.md.

## Done when

Every step has run, each approval was given, and you've reported what was produced and where it was saved.
```

## Usage Notes

Run it in Claude Code or Codex: save as .claude/skills/competitor-research-brief/SKILL.md (or .agents/skills/ for Codex) and say "run the Competitor research brief workflow"; parallel steps run as subagents. Or paste it into ChatGPT or Claude and answer its questions. It asks for: company, competitors. Build or run it step by step at prompts-gpt.com/workflows/competitor-research-brief.

Example output

At a glanceCompetitor research run at a glanceLead agent plan, parallel subagents and sourced claims for Loomwell
Competitors researched
3 subagents
StudioDesk, PoseBook, MatTime in parallel
Sourced claims collected
41 claims
Each with a source URL
Research questions in plan
5 questions
Pricing, audience, content, traffic, gaps
Openings for Loomwell
3 openings
Saved to research/competitors.md

Example for: company "Loomwell" (a scheduling app for independent yoga studios); competitors "StudioDesk, PoseBook, MatTime".

Run report: Competitor research brief

Plan (saved as plan):

  1. What do they charge, and at what tiers?
  2. Who is the core customer (studio size, region)?
  3. Which content or features get the most attention?
  4. Where does their traffic come from?
  5. What do customers complain about or ask for?

Subagents: 3 launched in parallel; all 3 returned. Results saved as notes (41 claims, each with a source URL).


research/competitors.md

Competitor Brief: Loomwell vs. StudioDesk, PoseBook, MatTime

Compiled from public pages and reviews; all figures are fictional demo data.

Comparison
StudioDeskPoseBookMatTime
Pricing$129/mo flat, 1 location$49–$189/mo, 3 tiers2.9% per booking, no monthly fee
AudienceMulti-location chains, 10+ instructorsMid-size studios in the US and CanadaSolo teachers and pop-up classes
Top content"Studio growth" webinar seriesFree class-schedule templatesInstagram reels of instructor stories
Traffic sourcesPaid search (~55%)Organic search (~60%)Social (~70%)
GapsNo mobile check-in; slow supportWeak payroll for instructorsNo memberships or class packs
3 Openings for Loomwell
  1. Own the 2–8 instructor studio. StudioDesk prices out small studios, and MatTime lacks memberships. A $69/mo plan with class packs fits the gap.
  2. Ship instructor payroll as a headline feature. PoseBook's top review complaint (18 of 40 recent reviews) is manual pay calculation.
  3. Compete on organic templates, not paid search. PoseBook proves templates drive traffic. Loomwell can publish a free "substitute teacher sheet" and "monthly timetable" kit aimed at keywords PoseBook doesn't rank for.
Sources
  • studiodesk.example/pricing
  • studiodesk.example/webinars
  • posebook.example/plans
  • posebook.example/templates
  • reviews.example/posebook (accessed 12 Mar)
  • mattime.example/how-it-works
  • social.example/@mattime
  • trafficstats.example/compare?sites=studiodesk,posebook,mattime

Done. All 5 steps ran, and no approval gates were triggered. The brief is saved to research/competitors.md. Two claims rely on a single review source and are worth a second check: PoseBook's payroll complaint count and MatTime's social traffic share.

Written by AI from this prompt. Your results will vary.

Run it in Claude Code or Codex: save as .claude/skills/competitor-research-brief/SKILL.md (or .agents/skills/ for Codex) and say "run the Competitor research brief workflow"; parallel steps run as subagents. Or paste it into ChatGPT or Claude and answer its questions. It asks for: company, competitors. Build or run it step by step at prompts-gpt.com/workflows/competitor-research-brief.

Make it repeatable

Keep using this prompt without pasting it in every time.

Prompt details

By
Prompts-GPT editors
Published
How prompts are written and checked

Did this prompt work?

Keep exploring

More in Multi-Agent Pipelines