NEW App Foundry — build agents, tools, workflows & whole apps from a prompt. Explore →
🏭 App Foundry

Describe the app. We build the agents, tools, workflows — and ship it.

App Foundry turns a plain-language prompt (plus the agent and workflow definitions you already own) into a durable, streamed build: PRD → blueprint → scaffold → generate → verify → deploy. The output isn’t a chatflow — it’s a self-sustaining app with its own database, container, tests, and run ledger.

  • PRD-first + HITL
  • Self-verifying (pytest + Playwright)
  • Self-hosted & multi-tenant
  • Run ledger
app-foundry.vastvic.com

Build a competitor-intel app: scrape rivals weekly, summarize pricing changes, email a digest, and expose an API.

Reporter agentweekly-researchClaude Opus 4.8
Forging
PRD generated · docs/PRD.md
scraper-mcp · 3 tools
summarize() → Claude Opus
reporter agent · wiring schedule…
PreviewCodeManage
Competitor Radar● live
Weekly digestNext run · Monday 9:00
6 competitors trackedscraper-mcp · updated 4m ago
Digest emailedreporter · 128 subscribers

Integrations & connectors, provisioned as MCP clients

SStripe GGoogle MS Intune SendGrid Twilio AAnthropic OpenAI GGemini
The build, in two screens

From a prompt to a running app you can watch being built.

Describe

An agent that researches competitors: scraper MCP, a summarizer tool, and a reporting sub-agent that emails a weekly digest.

+ Agent+ Workflow+ LLM
Hybrid modeHuman‑firstAgent‑first

1 · Build intent — prompt, attached definitions, build mode & surfaces

app-foundry.vastvic.com

Build a competitor-intel app: scrape rivals weekly, summarize pricing changes, email a digest, and expose an API.

Reporter agentweekly-researchClaude Opus 4.8
Forging
PRD generated · docs/PRD.md
scraper-mcp · 3 tools
summarize() → Claude Opus
reporter agent · wiring schedule…
PreviewCodeManage
Competitor Radar● live
Weekly digestNext run · Monday 9:00
6 competitors trackedscraper-mcp · updated 4m ago
Digest emailedreporter · 128 subscribers

2 · Orchestrator — live stage stream, gates, preview / code / manage

🧠 Deep Agents & Harness

How Vastvic’s deep-agent harness actually works.

Every build is driven by a harness — a durable ReAct loop with planning, sub-agents, memory, MCP tools, and human-in-the-loop interrupts. It’s the same substrate whether you’re forging one tool or a whole app.

🧠
Deep agentPlans with write_todos, reasons in a ReAct loop, compacts its own context.
🧩
Tools & MCPShell, file edit, web, SQL — and any MCP server as a governed tool.
👥
Sub-agentsSpawns specialists in parallel via the task tool; results stream back.
Self-verifyRuns build/test, feeds failures back, retries until green.
researcharchitectcodingreviewops
One forge, three outputs

A prompt goes in. Agents, workflows, and a running app come out.

The forge is the same substrate for every build — whether you’re shipping one agent or a whole app. Attach what you already own, or let the blueprint decide the rest.

App Foundry forge illustration: prompt to agents, workflows and a running app
Prompt → everything

One prompt generates agents, tools, workflows — and the app around them.

Attach the definitions you own or let the blueprint decide. The harness provisions MCP servers, registers tools, spawns sub-agents, and wires a workflow schedule — then generates the code that runs them.

  • Reasoning & workflow agents with personas, skills and harness bindings
  • MCP servers forged and mounted as first-class, governed tools
  • Workflows compiled into the build and executed by the flow engine
  • HITL interrupts on risky actions (execute / write / deploy)
  • Durable memory + a unified run ledger across every step
agent_runner.py
1# compiled from your build intent
2from foundry import Agent, MCP, tool
3 
4scraper = MCP("scraper-mcp")
5 
6@tool
7def summarize(text): return llm(text)
8 
9reporter = Agent("reporter",
10  tools=[scraper.fetch, summarize, send_digest],
11  harness="weekly-research", schedule="weekly")
🔌 Connectors

Every integration is a governed MCP tool.

Pick a connector and App Foundry provisions a real, MCP-callable connection through the unified gateway. Credentials are entered behind an HITL boundary — the agent never sees a raw secret until you approve it.

💳

Payments

Stripe, Razorpay, PayPal, Paystack — billing as a tool.

🔐

Auth & identity

Google sign-in, Microsoft Intune device gates.

Messaging

SendGrid, Twilio for email, SMS & verification.

🤖

Models

Anthropic, OpenAI, Gemini via unified model routing.

🛡 Governance & Run Ledger

Autonomous, but never unaccountable.

HITL gates

Per build mode: gate the blueprint, deploy, or every stage. Nothing risky runs without approval.

👤

RBAC & isolation

Tenant / space isolation and role-based access on every action, enforced at the gateway.

🧾

Unified run ledger

Every event, cost and token is traced — a complete, replayable record of the build.

🏖

Self-hosted

Runs on your infrastructure, multi-tenant by default. Your data never leaves.

Build your first app from a prompt.

Bring your agents and workflows — or start from a blank prompt. App Foundry forges the rest and ships a governed, running app on your infrastructure.