Define a team of specialists. Describe your goal. Watch 20+ AI agents deliver documents, analysis, and decisions — in minutes, not weeks.
Specialists run in parallel — each hands off to the next layer. You just write the brief.
What teams say about Forge
We cut our bid response time from 3 weeks to 4 hours. The compliance and commercial agents alone justify the cost.
Head of Proposals
Infrastructure consultancy, Dublin
Our DevSecOps review that used to take a sprint now runs overnight. The threat model output is genuinely better than what we wrote manually.
Engineering Lead
FinTech startup, London
Running a new business plan takes 22 minutes. We now evaluate 3x more opportunities per quarter without hiring more analysts.
Strategy Director
Private equity firm, Stockholm
The same deliverables you would commission from a consultancy — produced by coordinated AI agents.
Three steps from blank brief to polished deliverables.
Pick from 21 ready-made templates — DevSecOps, Bid Response, Business Plan, Due Diligence — or build a custom team from 100+ specialist roles.
21 templates · 100+ roles
Write a brief, or attach a PDF, Word doc, spreadsheet, or image — agents read your actual documents and even describe charts and screenshots via vision. The Brief Enhancer scores your input and flags missing context before agents start.
Multi-modal briefs · Brief scoring · Webhook trigger
Specialists run in sequence, each building on the previous. A live timeline shows every step with confidence scores. Download .docx, .pptx, or ZIP when done.
Live progress · Quality scores · .docx / .pptx export
A single AI prompt gives you one perspective. Forge gives you a coordinated team of specialists — each checking and building on the previous.
Bid Response
3–4 weeks
Bid manager + team
22 min
9 specialists
Analysis · Proposal · Legal review · M365 prompts
Due Diligence
3–5 days
Analyst + legal team
18 min
5 specialists
Financials · Risk register · Legal · DD summary
Compliance Audit
4–6 weeks
Compliance consultant
22 min
5 specialists
Gap analysis · Controls · Remediation roadmap
Based on typical professional timelines. Agent quality scores and confidence ratings visible on every run.
Four capabilities that make Forge different from every other AI tool.
Deployable on your own cloud. No vendor lock-in.
Real-time timeline as each specialist completes their work. Confidence scores, decisions, and reasoning all visible. No black box — total transparency into every step.
Assemble any combination of 100+ agent roles. Connect web search, Jira, Slack, and webhooks. Set per-agent goals. Conditional routing on outcomes.
Attach PDFs, spreadsheets, images, and documents to your brief. Agents read them directly — no copy-paste, no pre-processing, no extra setup.
Every completed run teaches the system about your organisation. Future runs automatically get context from previous work — so results improve over time without any extra effort.
Beyond running teams — Forge learns from every run, lets you steer in real time, and is fully observable.
Every run is scored by an AI evaluator. Forge spots the weakest agent, proposes a sharper prompt, A/B-tests it against the current one, and lets you apply the winner — with one-click rollback.
Guide a team while it works — "focus on EU compliance", "keep it under 2 pages". The directive folds into every downstream agent at highest priority. No cancel, no restart.
A per-agent execution trace on every finished run — duration, tokens, confidence, and cost. A non-destructive trust check flags potential PII and secrets before you share a deliverable.
Publish your teams, earn star ratings and reviews, and build a public creator profile. A leaderboard ranks the top creators by adoption — social proof that compounds.
Connect runs together, trigger from external systems, and route actions based on confidence scores.
Outputs from one run automatically trigger the next pipeline. Build multi-stage workflows that run end-to-end without manual intervention.
GitHub PR opened, Jira ticket created, or any webhook fires — Forge detects the event and starts the right pipeline automatically.
Set fire conditions on confidence scores. High confidence fires automated actions. Lower scores hold for human review before anything is posted.
Each template is a pre-built team of specialist agents, pre-wired to hand off work in sequence and produce a complete deliverable.
Business & Finance
Market analysis, competitive landscape, financial model, strategy document, and investor-ready plan
Business & Finance
Traction validation, market sizing, financial projections, pitch narrative, and investor Q&A prep
Business & Finance
KPI dashboard, risk register, CEO narrative, and complete board pack with RAG status
Business & Finance
Spend analysis, financial forecast, scenario planning, and board-ready budget plan
Legal & Compliance
Clause analysis, risk register, legal assessment, and negotiation strategy
Legal & Compliance
GDPR, ISO 27001, SOC 2 — gap analysis, controls assessment, and remediation roadmap
People & HR
Role analysis, compensation benchmark, job description, interview guide, and offer package
People & HR
Objectives review, feedback synthesis, development plan, and complete review document
Strategy
Financial analysis, risk register, legal review, and executive recommendation with confidence score
Strategy
Market sizing, user personas, competitive map, RICE prioritisation, and full PRD
Strategy
Requirements spec, vendor research, scoring matrix, and recommendation report
Strategy
Current state mapping, bottleneck analysis, future state design, and implementation plan
Strategy
Literature review, data synthesis, key insights, and evidence-based report with recommendations
Strategy
Strategy, market scouting, vendor shortlist, RFP, due diligence, negotiation, contract heads of terms, and executive report
Tech
Requirements, architecture, threat model, IaC, implementation plan, test strategy, cost estimate
Tech
Threat modelling, OWASP Top 10, dependency CVEs, pentest findings, remediation roadmap
Tech
Pull AC/DoD from Jira/GitHub, locate the feature code, audit quality, score DoD coverage, dual report
Tech
Code analysis, API reference, user guides, changelog — all generated from your codebase description
Content & Marketing
Tender analysis, requirements matrix, capability matching, proposal, legal review, M365 prompts
Content & Marketing
Strategy, audience personas, copywriting, SEO plan, and 90-day execution calendar
Content & Marketing
Prospect research, competitive analysis, tailored pitch, objections, outreach sequences
Content & Marketing
Audience analysis, topic research, editorial themes, and 90-day content calendar
All 22 templates included free. No credit card required.
Start for freePick from 100+ specialist agent roles and assemble a custom pipeline for your exact use case. An AI advisor checks your team composition before you run.
Don't build your own AI platform — run on Forge. REST API, TypeScript SDK, and a command-line tool. Define agent teams in code, stream into your UI, embed live run views, and give agents persistent memory.
import { ForgeClient } from '@forge/sdk'
const forge = new ForgeClient({
apiKey: process.env.FORGE_APP_KEY,
})
// Submit a run and stream results
const run = await forge.createRun({
team_id: 'devsecops-team-id',
title: 'Q3 Security Audit',
brief: 'Review our Node.js API...',
})
for await (const frame of forge.streamRun(run.id)) {
if (frame.type === 'event')
console.log(frame.data.agent_role, '→', frame.data.title)
if (frame.type === 'done')
console.log('Status:', frame.data.status)
}
const { outputs } = await forge.getRunOutputs(run.id)
// outputs: risk register, remediation plan, report...Create runs, deploy teams, stream events, manage memory, query usage. Scoped API keys, full OpenAPI 3.0 spec, interactive reference.
View OpenAPI spec →Zero-dependency. Node, Deno, Bun, browser. Typed runs, teams, memory, SSE streaming, stream tokens, and a runAndWait() helper.
SDK quick start →npm install -g @forge/cli. Create runs and watch agents work live in your terminal, deploy teams, manage memory. Ideal for CI/CD pipelines.
CLI docs →Define teams in a version-controlled forge.yaml and reconcile with forge iac plan / apply — idempotent, reviewable in PRs, and safe to run from CI.
IaC docs →Consumer apps get:
Everything you need to ship AI features
Issue keys with granular scopes — runs, outputs, teams, memory, usage. Self-serve from the developer portal.
Deploy a full agent team from a JSON manifest via POST /teams. No dashboard — version teams in your repo, deploy in CI.
Short-lived stream tokens let your frontend open an EventSource and show live agent progress — without exposing your key.
Drop a live run timeline into any app with a single <iframe>. Status, events, outputs, and usage — Forge-hosted, zero CSS.
Store per-user and app-wide facts. They are auto-injected into future run briefs — persistent context with no vector DB to run.
forge run create streams agents live in your terminal. Deploy teams, manage memory, script anything. Perfect for CI/CD.
Three things every decision-maker needs to know before signing off on Forge.
Org Impact Dashboard
Every Forge account includes a live impact dashboard. See your team's runs, hours saved, EUR value, cost, and ROI — updated in real time. Share it as a public link for board reporting or procurement review.
Every account belongs to an organisation. Invite your team by email — they land on a branded acceptance page and are added instantly. Role-based access keeps the right people in control.
For large organisations that need more control, compliance, and flexibility. Deploy on your own cloud infrastructure — your environment, your data, your rules.
Security & compliance
Row-level security
Enforced on every database table
Secrets in a vault
Hardware-backed, never in code
AES-256-GCM encryption
Secret Vault for agent credentials
GDPR compliant
EU data residency, right to erasure
Start free. Upgrade when you need more runs or seats. No hidden fees.
Trial
Get started and explore the platform.
3 seats
10 runs / month
Starter
For small teams running regular pipelines.
10 seats
100 runs / month
Pro
For growing teams that run at scale.
25 seats
500 runs / month
Enterprise
Tailored contracts, SLAs, and volume pricing.
Unlimited seats
Unlimited runs
All prices in EUR, billed monthly. No setup fees. Cancel anytime from your billing portal. Limits reset on the 1st of each month.
Add Forge to your home screen on iOS or Android for a full native experience. Receive push notifications the moment a run completes — wherever you are.
How is Forge different from ChatGPT or Copilot?
ChatGPT is a single assistant. Forge runs a coordinated pipeline of specialist agents — each with a defined role, context from prior agents, and structured output. The result is a complete deliverable (a 30-page business plan, a full bid response), not a chat reply.
What LLMs does Forge use?
Forge runs on Azure AI Foundry, currently using GPT-4 class models. All inference runs within the EU by default. Enterprise plans can request specific model versions or bring their own Azure subscription.
Is my data secure and private?
Yes. All data is encrypted in transit (TLS 1.3) and at rest (AES-256). Row-level security means no user can access another organisation's data. Agent credentials are stored in a hardware-backed vault, never in code or logs. See our Security page for the full picture.
Can I self-host or deploy on my own cloud?
Yes — the Enterprise plan includes an on-premise or private cloud deployment option. You bring your Azure subscription and we handle the deployment. Your data never leaves your infrastructure.
How long does a run actually take?
Most templates complete in 15–25 minutes. Larger pipelines (DevSecOps with 9 agents, Bid Response with 9 agents) take up to 30 minutes. Independent agents run in parallel to minimise total time.
Can I build custom teams beyond the 20 templates?
Yes. Pick any combination of 100+ specialist agent roles, set per-agent goals, connect tools (web search, Jira, Slack), and define hand-off conditions. An AI advisor reviews your team composition before you run.
Can I build my own product on top of Forge?
Yes — Forge is designed to be the AI infrastructure layer for your app. Use the REST API, TypeScript SDK, or CLI to create runs, deploy teams from a JSON manifest, stream live progress into your UI, embed a run timeline with a single iframe, and store persistent memory that's auto-injected into runs. Self-serve a scoped API key from the developer portal — no sales call needed.
Request early access and we'll have you running your first pipeline within 24 hours. No credit card, no setup fees.
Already have access? Sign in →
A deep-dive into how leading organisations are deploying AI agent teams to compress weeks of knowledge work into minutes — with real ROI data, architecture details, and a security & compliance overview.