Consensus

Search engine that answers questions from peer-reviewed research

NOT REALLY · consider alternatives
price variesestimated build time not a true replacement; consolation build in one to two daysreplaced by 0 people

Do not mistake the interface for the product. Consensus's durable value is data, import reliability, which a solo one-shot build cannot reproduce responsibly. The prompt therefore builds only the closest honest personal consolation tool.

Build verification: not recorded. How we judge buildability

Product and project scope

Consensus searches academic literature and uses AI to explain the papers it retrieves. Its documented process combines keyword and semantic matching, ranks research results and produces summaries linked to citations. Users can explore an individual paper or synthesize findings across several papers, with search modes supporting different levels of analysis. That makes it a discovery and evidence-navigation tool, rather than only a chat window over uploaded files. The usefulness of a smaller replacement depends on which research corpus it can actually search.

Product sources: Consensus: how it works (retrieved 2026-10-26) · Consensus Help: search and best practices (official search excerpt 2026-10-26)

Proposed workflow
Build a private AI academic search workspace that imports user-supplied URLs or files, extracts metadata, supports notes, and searches the local corpus.
Recorded effort estimate
not a true replacement; consolation build in one to two days. This applies to the limited workflow; setup, approvals, recovery and ongoing maintenance can change the effort.
Complexity boundary
consolation build only; the paid product's moat remains
Operating responsibility
Maintain parsers, deduplication, PDF extraction, citation styles, and legal access boundaries.

Assumptions behind the estimate

Build verification is not recorded. The plan and acceptance checks describe work to perform, rather than a completed implementation. Product feature sources do not reverify the older pricing entries below.

What you give up

  • publisher-specific import reliability
  • citation graph scale
  • team libraries and institutional access
  • licensed scholarly metadata

Why people still pay

Consensus: Researchers pay for correct metadata, resilient importers, citation coverage, and workflows that survive publisher and browser changes.

Your build guide

The stack, security requirements, and agent rules for a focused replacement.

Before you start

  • Node.js 22
  • browser automation for user-authorized imports
  • optional OpenAI API key stored in .env
  • Explicit README warning that this is a consolation build, not a production replacement
01
Use exactly this stack: Next.js 15 + TypeScript + SQLite + Playwright.
02
Model source URLs, saved items, reading state, annotations, and exports; keep stable source IDs and timestamps.
03
Interface for this AI academic search workflow: a local web page with input, progress, review, and export views.
engineering roadmap

Implementation plan

1

Phase 1, architecture and data

Use exactly this stack: Next.js 15 + TypeScript + SQLite + Playwright. Model source URLs, saved items, reading state, annotations, and exports; keep stable source IDs and timestamps.

2

Phase 2, implement

For AI academic search, accept a user-supplied URL or file and save its original URL, fetch time, and content hash.

3

Phase 3, implement

Extract readable content, deduplicate imports, and preserve notes or highlights by stable source position.

4

Phase 4, review and output

Search the saved collection and export an item with its source metadata.

5

Phase 5, recovery and acceptance

Verify this invariant with a saved fixture: An unreachable URL keeps its bookmark and error state; duplicate imports must not discard existing highlights. State the practical limit: publisher-specific import reliability.

the pro prompt
Build me a focused AI academic search workflow for the personal core of Consensus. Requirements:

- Use exactly this stack: Next.js 15 + TypeScript + SQLite + Playwright. Model source URLs, saved items, reading state, annotations, and exports; keep stable source IDs and timestamps.
- Paid product context: Search engine that answers questions from peer-reviewed research. Build only this DIY scope: Build a private AI academic search workspace that imports user-supplied URLs or files, extracts metadata, supports notes, and searches the local corpus.
- For AI academic search, accept a user-supplied URL or file and save its original URL, fetch time, and content hash.
- Extract readable content, deduplicate imports, and preserve notes or highlights by stable source position.
- Search the saved collection and export an item with its source metadata.
- Use a local web page with input, progress, review, and export views. Required input or access: browser automation for user-authorized imports; optional OpenAI API key stored in .env. Keep credentials in .env.
- Acceptance: with one labelled sample, show the input, saved intermediate state, and exported result; verify this invariant: An unreachable URL keeps its bookmark and error state; duplicate imports must not discard existing highlights.
- Out of scope: publisher-specific import reliability; citation graph scale. Keep this a personal, inspectable workflow.
- Include a README with setup, a sample input, required keys or permissions, data location, and the supported scope.

$ open in your agent (prompt prefilled, you press enter), copy the prompt or copy AGENTS.md · generated from this app's build plan

share on X ↗

Alternatives to building your own

no votes, no pay-to-list · just what's real

Consensus pricing

planmonthlyannual (per mo)what you get
free$0/user$0/userUnlimited Papers searches; 15 Pro messages/month; 3 Deep Reviews/month; 10 Study Snapshots/month.
pro$20/user$12/userUnlimited Papers searches and Pro messages; 15 Deep Reviews/month; unlimited Study Snapshots.Annual charge is $144.
deep$65/user$45/user200 Deep Reviews/month.Annual charge is $540.
teams——Up to 200 seats; 50 Deep Reviews/user/month.Quote-based.
enterprise——More than 200 seats; custom security, billing and usage.Quote-based.

free tierunlimited Papers searches; 15 Pro messages/month; 3 Deep Reviews/month; 10 Study Snapshots/month

billingmonthly + annual for Pro and Deep; Teams and Enterprise quote-based

hidden costsstudent and faculty discounts are 40%; eligible clinicians receive 25%; team price scales by seat

pricing sources checked 2026-08-13 · pricing source ↗

Questions about Consensus

Can you build your own Consensus with AI?

A full replacement is not the recommended project. Do not mistake the interface for the product. Consensus's durable value is data, import reliability, which a solo one-shot build cannot reproduce responsibly. The prompt therefore builds only the closest honest personal consolation tool.

What does the Consensus build prompt cover?

The prompt starts with this scope: Build a private AI academic search workspace that imports user-supplied URLs or files, extracts metadata, supports notes, and searches the local corpus. Full-product capabilities excluded from the comparison include: publisher-specific import reliability; citation graph scale; team libraries and institutional access. Follow the implementation plan and its prerequisites before expanding the build.

How do I use the prompt, AGENTS.md and agent skills?

Start with the Consensus prerequisites and stack, then copy the prompt into your coding agent. Save the project rules as AGENTS.md in the project root. Linked skills are optional packages or source instructions for specific tasks; review their current contents and install only those matching the chosen stack. A skill does not supply API credentials or verify the finished app.

How long will this Consensus project take?

The catalogue estimate is not a true replacement; consolation build in one to two days for the limited scope. Setup, integration approvals, debugging, deployment and ongoing maintenance can add time. This is an estimate, not a delivery guarantee.

What would I give up by replacing Consensus?

publisher-specific import reliability; citation graph scale; team libraries and institutional access; licensed scholarly metadata. Consensus: Researchers pay for correct metadata, resilient importers, citation coverage, and workflows that survive publisher and browser changes.

What can I use instead of building Consensus?

Ai2 Asta: Ask a scientific question and get a cited mini-review instead of a confidence meter. Check each option's license, hosting needs and feature limits.

Every week, more subscriptions die.

New verdicts, new prompts, the week's most-doomed apps.
One email. Unsubscribe in one click.

free forever · no scanner spam · the prompt stays on the site, the deaths come to you

$weekly: what got a verdict, what died.