Developer Docs
Three layers, one mental model: Guides for "how do I accomplish X?", API Reference for "what are the endpoints?" (Swagger/Scalar, canonical), and Tutorials for end-to-end projects. The Playground is the interactive companion to all three. Agents can ingest the whole library in one file: llms-full.txt.
User journeys grouped by the same families as the home page and Playground.
Platform-wide
G-00
Your first API call in 5 minutes
Pick an environment, prove a service is alive, present your key pair, and make one safe authenticated call.
G-01
Authentication & sessions
Discover the sign-in methods a tenant supports, complete a sign-in, handle the token pair, refresh it, and sign out.
G-02
Calling services from an AI agent (MCP)
Discover a service's agent-facing tools over MCP, list them, and call one — no API wrappers to write.
G-03
Errors, retries & idempotency
Read platform error statuses correctly, retry only what's retryable, and design writes so retries are safe.
G-04
Uploading files the platform way
Upload a file through the CDN, handle the already-exists conflict with overwrite, read it back, delegate access with a time-limited token, and delete it.
Applied Intelligence
G-10
Your first AI chat session
Create an Evergreen AI session with model-selection criteria, send a message, stream the reply, and end the session cleanly.
G-11
Grounding answers in your documents
Upload documents to a RAG collection, query them with hybrid semantic search, and wire the collection into an Evergreen AI chat session.
G-12
Detecting objects and poses in images
Upload an image and get back labeled bounding boxes for every object and 17-keypoint skeletons for every person, with relative coordinates and confidence scores.
G-13
Choosing Evergreen vs Bella vs Chloe
Three AI surfaces, one platform — sessions you configure, sessions pre-tuned for you, and impromptu reasoning that trades budget for depth.
Our AI Models
G-20
Chatting with Bella
One OpenAI-compatible call to a warm, pre-tuned assistant — persona, model pick, and safety posture already handled. Bring only a message.
G-21
Chatting with Chloe
One OpenAI-compatible call where the service decides how much reasoning your question deserves — a budget knob trades cost and latency against answer depth.
Users & Profile Matching
G-30
Managing users & profiles
Read your own profile from Users Query, flesh it out with Users Command (get-modify-put), discover users via search and batch reads, and remove a user — then watch it be born again at the next sign-in.
G-31
Federated sign-in for your app
Ask the Auth Service which sign-in methods your app may offer, complete a federated Google/Apple sign-in end-to-end, start the passkey ceremony, and rotate or revoke the session that comes back.
G-32
Finding matches between profiles
Create a matchable collection, index JSON profiles into it, and rank them against a query with top-K cosine search — then filter by a similarity threshold and clean up.
Communication
G-40
Publishing and reading a feed
Post to the feed from your app, watch the moderation pipeline publish it, read and search the timeline, edit as the author, and clean up — across the Feed Command / Feed Query CQRS pair.
G-41
Direct messaging between users
Create a conversation between users, send messages that pass through the moderation pipeline, read and poll the thread, edit and react, track delivery/read receipts, and clean up — across the Messaging Command / Messaging Query CQRS pair.
Media
G-50
Transforming audio, images & video
Trim, transcode, resize, and upscale media with the three transformer services — audio and video as asynchronous jobs (video reports completion over SSE), images as synchronous binary responses — all keyed by local source_path files.
G-51
Scrubbing PII from text
Redact emails, phones, credit cards, IPs, and URLs into stable placeholders before text leaves your perimeter, then deanonymize later to restore the originals — structural detection that works identically across languages.
Translation & Voice
G-60
Translating text with Linga
Translate single texts between BCP-47 locales with optional domain jargon and generational vernacular, auto-detect the source language, or run a bidirectional language-pair channel that flips direction on its own — all through one REST endpoint pair fronting Evergreen AI.
G-61
Cloning a voice and speaking
Register a VoicePrint from a microphone recording (pre-recorded or consent-script verified), then synthesize speech in that voice — as binary MP3/WAV or as an SSE stream of PCM chunks — on the Speech service's local Qwen3-TTS model.
G-62
Verifying audio provenance
Check whether an audio clip was produced by this platform — the Speech service watermarks every synthesized clip invisibly, and one multipart call returns a verdict, a confidence score, and (when the payload survives) the voice-print hint and request ID that created it.
Infrastructure & Storage
G-70
Caching with Memcache
Add, read, expire, and delete tenant-isolated key-value entries on the shared Memcache service — exact-match caching with TTLs, a private loopback router for prefix listing and diagnostics, and MCP tools for agents.
G-71
Storing & serving files with the CDN
The CDN Service as tenant-scoped storage infrastructure — per-user ownership with 403 enforcement, time-limited download tokens (and what they do and don't exempt), delete lifecycle semantics, path-safety validation, limits and quotas, and MCP tools for agents.
Interactive OpenAPI docs per service — Swagger UI and Scalar. These are canonical; guides never duplicate them.
Multi-service, narrative projects with checkpoints. Planned per DOCS-PLAN.md §5 — shipped pages replace their card.
T-01 · Intermediate · ~45 min
Build a support assistant
Ingest an FAQ corpus, ground an Evergreen AI chat session on it, and alert users when answers arrive.
T-02 · Intermediate · ~60 min
Build a social app backend
Users, profiles, a feed timeline, and direct messages — the full Communication stack composed end-to-end.
T-03 · Beginner · ~30 min
Build a media pipeline
Upload once to CDN, derive resized/transcoded variants, and cache derivatives for fast repeat access.
T-04 · Advanced · ~60 min
Build a multilingual voice assistant
Chat in one language, translate with Linga, and speak the answer with a cloned VoicePrint.
T-05 · Advanced · ~45 min
Agentic inventory audit
Agent-first: drive an AI agent over the platform's MCP surfaces to audit inventory and log findings.