01
Call from your backend
Send the user request and stable app user id from trusted server code.
Agent backend
The agent backend for your app.
General Augment helps product teams embed governed agents into existing apps. Your app keeps the UX, auth, billing, permissions, and source of truth. General Augment provides the backend layer around the agent.
Server-side agent backend
01 App backend
Calls /v1/responses
Project key stays server-side
02 User context
Memory and identity resolve
Stable app user id
03 Tools
Allowed actions load
OpenAPI, MCP, private connectors
04 Result
Reply, usage, and trace return
Support-ready evidence
Your app keeps the surface and source of truth. General Augment returns the reply, trace, usage, and audit evidence your team needs to operate the agent.
What the backend adds
Backend API for app-originated agent turns
Stable app-user identity for memory, usage, traces, and approvals
Durable memory APIs for useful facts, summaries, and profile context
Governed tools from app APIs and approved connector actions
Approval gates for sensitive writes and external side effects
Observability for response IDs, trace IDs, usage, tools, and channels
Integration path
Start with one server-side call. Add controls as the agent gets useful.
General Augment is designed for incremental adoption: first response, then memory, tools, approvals, channels, and private connectors when the product needs them.
02
Add memory when it matters
Store facts, preferences, summaries, and profile context against that app user.
03
Expose app tools deliberately
Import OpenAPI tools or connector actions, classify risk, and require approval for sensitive writes.
04
Operate with evidence
Use response ids, traces, usage, tool events, and approval records for support and billing.
Compare build paths
raw LLM APIs
LLM API vs Agent Backend
The agent lives inside an existing product.
Compare
agent frameworks
Agent Framework vs Managed Agent Backend
You want an app-agent backend instead of a custom platform project.
Compare
OpenAI Agents SDK
OpenAI Agents SDK vs Agent Backend
The agent belongs inside an existing product experience.
Compare
Vercel AI SDK
Vercel AI SDK vs Agent Backend
You need a managed backend that existing app backends can call.
Compare
First call
The API shape is familiar on purpose.
Product teams can start from a Responses-compatible route while General Augment handles the app-agent backend concerns around it.
curl https://api.generalaugment.com/v1/responses \
-H "Authorization: Bearer $GENAUG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "balanced",
"user": "app-user-123",
"input": "Summarize this account and suggest the next action"
}'Your app keeps
- Product UX and customer relationship
- Auth, billing, app permissions, and source of truth
- Business rules and app-owned side effects
General Augment provides
- Agent turns through a server-side backend API
- Memory, tools, approvals, channels, usage, and traces
- Optional private connectors for your own capacity