The contextual backbone for your engineering team and AI agents.

Manage features, solution designs, tests and architecture decisions in one place, then hook that knowledge directly into coding agents and IDEs so everything gets built from a place of full contextual awareness.

AI agents work better with real business context

Without project knowledge, agents guess. With Specsource, they get it right first time.

Without Context
freshcart.comFree delivery over $75FreshcartSearch groceries...promotional bannerFresh groceries, delivered fastShop nowFruitDairyBakeryDrinksOrganic Avocados4 pack$5.99Free-Range Eggs12 pack$4.49Sourdough Loaf500g$3.99Oat Milk1 litre$4.29Earn with Fresh Cart Pointsfreshcart.com
With Context
freshcart.comFree delivery over $50FreshCartSearch groceries...promotional bannerFresh groceries, delivered fastShop nowFruitDairyBakeryDrinksOrganic Avocados4 pack$5.99Free-Range Eggs12 pack$4.49Sourdough Loaf500g$3.99Oat Milk1 litre$4.29Earn with FreshRewardsfreshcart.com

Describe how you want to build it, so engineers and agents are aligned

Describe how you want to build it. AI reads your specs and proposes changes. You accept or reject each one with full traceability.

Design
Plan
Build
Test
Verify
Iterate
Business ContextCTX-
FeatureFEAT-
TestTEST-
ReportRPT-
ADR / DecisionADR-
InstructionsINST-
SystemsSYS-
Data FlowsFLOW-

AI-powered synthesis

Feed in API docs, meeting notes, Figma designs, PDFs. Specsource synthesises them into structured specifications for your approval.

GET/api/v1
{  id: 1,}
.tsx
export async function() { const data}
PDF
Notes
- Auth needs SSO- Rate limit APIs- Q3 deadline
PRD
Figma
AI Synthesis
7 extracted
0 accepted0 rejected7 pending
Features (3)
MFA for admin roles
Enforce multi-factor authentication for all users with admin permissions.
API key rotation
Allow workspace admins to rotate API keys without downtime.
Audit log export
Export audit logs as CSV or JSON for compliance reporting.
Initiatives (1)
Security hardening phase 2
Background: SOC 2 audit findings. Goal: address all critical and high findings by Q3.
ADRs (1)
TOTP over SMS for MFA
TOTP preferred for security. SMS fallback rejected due to SIM-swap risk.
Tests (2)
MFA enrolment flow
Verify QR code generation, TOTP validation, and recovery code display.
API key rotation without service interruption
Rotate key while active requests are in flight. Assert zero failed requests.

Write tests your team can read and agents can generate

AI agents read your features and designs, then generate test cases automatically. Run them step by step and share interactive reports with clients.

Create and run tests
SummaryLast Run
User sign-up flow
New user fills in email, password and name, receives a welcome email and lands on the dashboard.
passing2 hours ago
Add item to basket
Tap a product card, choose size and colour, then verify the basket count and total update correctly.
passing2 hours ago
Checkout with saved card
Complete a purchase using a saved payment method and confirm the order confirmation screen shows.
passing2 hours ago
Search returns results
Type a product name in the search bar and verify matching results appear within two seconds.
passing2 hours ago
Product image gallery
Swipe through product images and check that zoom, pinch and full-screen mode all work correctly.
passing2 hours ago
Push notification opt-in
First-time user is prompted to allow notifications, and the preference is saved to their profile.
passing2 hours ago
Password reset email
Request a password reset, open the email link and set a new password successfully.
passing2 hours ago
Dark mode toggle
Switch between light and dark themes and verify all screens render with the correct colour palette.
pendingNot run yet.
Sharable test report
Acme Store
Mobile App
Sprint 14 Regression Suite
2 Apr 2026, 14:32
3m 42sstaging
8
Total
7
Passed
0
Failed
1
Skipped
88%
Pass rate
User sign-up flow
passed1.2s
Add item to basket
passed4.8s
Checkout with saved card
passed3.1s
Search returns results
passed0.9s
Product image gallery
passed2.3s
Push notification opt-in
passed2.1s
Password reset email
passed1.4s
Dark mode toggle
skipped-

Set the rules once — for your team and every agent

Stop repeating context in every prompt or onboarding doc.

Define coding conventions, architecture rules and project background once. Agents fetch the full picture via MCP so they build from awareness, not assumptions.

Agent Instructions
# Auth Rules
- User IDs are text (Clerk), not UUID
- All RLS policies use auth.jwt() ->> 'sub'
- Every server action checks permissions

# Naming
- Files: kebab-case
- CSS modules: camelCase classes
- Imports: s from './component.module.css'
Copy Prompt or MCP

Generate a ready-to-paste prompt from your project instructions, or let agents pull them automatically via MCP.

Generated prompt

You are working in a Next.js 16 project with Clerk auth and Supabase. User IDs are text strings (Clerk format), never UUIDs. All RLS policies must use auth.jwt() ->> 'sub'. Follow kebab-case file naming and camelCase CSS module classes.

One source of truth for distributed teams

Different timezones, different locations, same specification. Specsource keeps every contributor aligned.

SOLUTION DESIGNPayment Gateway IntegrationOverviewArchitectureAPI ContractsError HandlingTesting StrategySarahLondonCarlosMadridYukiTokyoMarcusNew YorkPriyaBangaloreONLINESSarahLondonCCarlosMadridYYukiTokyoMMarcusNew YorkPPriyaBangalore
Sarah · London
Carlos · Madrid
Yuki · Tokyo
Marcus · New York
Priya · Bangalore

Let clients ask questions about the project

Share a portal link with stakeholders. They ask questions in plain English and get answers sourced from your specs, decisions and tests. No login required.

BadCat Software
Platform API
Project Knowledge Base

Ask questions about the project in plain English. Results are sourced from specs, decisions, features, and tests.

Ask

JWT was chosen over server sessions for stateless horizontal scaling. The decision was driven by the need to scale auth across multiple regions without shared session state. TOTP-based MFA was selected over SMS due to SIM-swap security risks.

JWT over server sessionsprimary
TOTP over SMS for MFAsupporting
SSO via SAML 2.0related
Auth: SSO token validationrelated
What are the trade-offs of JWT?How does token refresh work?Which tests cover the auth flow?

Your IDE reads your specs via MCP

Connect Specsource to Cursor, Claude Code or any MCP-compatible tool. Your agent fetches features, decisions and test cases before writing code, so it builds what you designed.

specsource - mcp@cursor
# specsource MCP — acme-platform
> get_feature_context "subscription billing"
✓ Feature: FEAT-037 Subscription billing
✓ Design: SD-012 Payment service architecture
✓ Decisions: ADR-005 Stripe over Paddle
✓ Tests: 3 cases (subscribe, upgrade, cancel)
✓ Rules: 3 agent instructions loaded
→ Context ready
> search_entities query="payment retry"
ADR-011 Exponential backoff for payments (decision)
TEST-089 Retry after card decline (test)
get_feature_context

Get everything an agent needs to build a feature — spec, linked designs, ADRs, tests, and instructions in one call.

search_entities

Search across all entity types — features, tests, designs, and decisions — by keyword.

get_test

Retrieve a test by ref with all steps, expected results, and linked features.

get_project_context

Everything in one call — instructions, features, decisions, systems, tests, and business context.

Features

Define what your product does with acceptance criteria, user stories, and goals.

Architecture Decisions

Record the why behind technical choices. Context, alternatives, and consequences.

Tests & Reports

Structured test cases with steps and expected results. Share reports with clients.

Agent Instructions

Per-project AI coding guidelines that carry across all agent implementation threads.

Systems & Data Flows

Map your architecture. Define services, databases, and how data moves between them.

Tags & Relationships

Cross-link any entity. Tests verify features, features implement designs.

Frequently asked questions