reload.wtf
← Blog
#agents#adk#google#devtools

Google ADK: the agent runtime, not another chatbot SDK

What Agent Development Kit actually is — build, run, evaluate, deploy — and when it is the right layer vs rolling your own loop.

ADK is Google’s open-source Agent Development Kit: a framework for building, debugging, evaluating, and deploying agents as software — not as one-off chat scripts.

It is the same family of ideas powering agent surfaces inside Google’s own products. Public docs position it as multi-language (Python first, plus TypeScript, Go, Java, Kotlin) and model-agnostic enough to not lock you into a single vendor API for every call.

What problem it solves

Raw LLM APIs give you tokens. Chat UIs give you a transcript.

Production agents need:

ADK is aimed at that stack. Think “agent application framework,” not “wrapper around generateContent.”

Mental model

LayerADK’s jobYour job
Modelcall through adapters / providerspick models, cost/latency tradeoffs
Agentdefine behavior, tools, handoffsdomain judgment, prompts, policies
Runtimerun the loop, stream events, keep sessionboundaries: secrets, blast radius
Evalharness patterns for agent qualitygolden tasks, failure cases
DeployCLI / API / cloud packaging pathsproduct shell: auth, tenancy, UI

If you skip that split, you either reimplement a half-broken runtime or bury product logic inside framework glue.

Core pillars (the official story, restated)

  1. Build — agents + tools, from single agent up to multi-agent workflows
  2. Interact — run locally, inspect traces/events, not black-box “it said OK”
  3. Evaluate — treat agent behavior like software under test
  4. Deploy — ship the same definitions beyond your laptop

The interesting part is orchestration: not only free-form “agent goes brrr,” but workflow-style agents when you want predictable pipelines (A then B then human gate).

That matches how serious agent products actually ship: autonomy inside a fence, determinism at the edges.

ADK vs “just use LangGraph / Crew / custom”

Peers solve overlapping problems. ADK’s pitch is:

Choose ADK when you want a standard agent runtime and are fine adopting its primitives (agents, tools, sessions, runners).

Roll your own or pick another framework when:

Framework churn is real. Keep domain logic thin at the ADK boundary: tools and policies should survive a runtime swap.

What “good ADK usage” looks like

root agent (orchestrator)
  ├─ specialist A + tools
  ├─ specialist B + tools
  ├─ shared session / context
  └─ human approval before irreversible side effects

Bad usage:

Same rules as any agentic system: verify in the loop, sandbox the blast radius.

Decision rule

Use ADK when you are building an agent product or multi-agent system and need a maintained runtime for sessions, tools, and composition.

Do not use ADK when you only need a single LLM call with a function or two — that is an API client, not an agent framework.

ADK does not replace product engineering. It replaces the part where every team reinvents the agent loop poorly. The judgment — what to automate, what to gate, what “done” means — is still yours.

get new posts

Occasional notes on agentic development. No spam.