Everruns Support Agent
Search and read citable documentation before answering Framework questions.
Answer Framework questions by searching and reading a small, inspectable corpus of official documentation. The agent retrieves evidence before answering instead of routing keywords to prewritten responses.

What you learn
Section titled “What you learn”A two-step search/read tool interface, citable evidence, and an explicit boundary around the available knowledge.
Scenario and expected outcome
Section titled “Scenario and expected outcome”The default question asks how to resume a durable session after restarting a process. The agent should search for persistence and session history, read the relevant pages, then explain the local catalog, persisted SessionId, and agent reattachment requirements with source URLs.
It must not imply that Engine::new() survives a restart. When the corpus lacks an answer, it should say so instead of inventing one.
Run it
Section titled “Run it”Install Rust/Cargo, clone the repository, and run from its root. This folder is self-contained within the workspace: its Cargo manifest references local Framework crates, so copying the folder alone is not sufficient.
git clone https://github.com/everruns/everruns.gitcd everrunsexport ANTHROPIC_API_KEY="your-key"cargo run -p everruns-framework-support-agentThe configured model is claude-opus-5-5. Provider access and funded credits are required. Keep keys in your environment, not in source control. Missing credentials, provider errors, and unsuccessful turns exit nonzero.
Try another question:
cargo run -p everruns-framework-support-agent -- "How do I register a custom provider?"cargo run -p everruns-framework-support-agent -- "How can a tool return a structured error?"Or type a question interactively:
cargo run -p everruns-framework-support-agent -- --interactiveBuild the agent
Section titled “Build the agent”Tools retrieve evidence; Opus decides what to search, read, and explain.
pub fn build(provider: impl Into<everruns::Provider>) -> Result<Agent, BuildError> { Agent::builder() .name("everruns-support-agent") .instructions(include_str!("resources/instructions.md")) .provider(provider) .model(MODEL) .max_iterations(12) .tool(tools::search_docs()) .tool(tools::read_doc()) .build()}Send, observe, and wait
Section titled “Send, observe, and wait”The shared demo helper subscribes before sending, shows bounded tool previews, waits for completion, and rejects unsuccessful turns. Use session.send_and_wait(&question).await? when a live tool timeline is unnecessary.
// ANTHROPIC_API_KEY, declared by the Anthropic driver itself.let agent = agent::build(everruns::Anthropic::from_env()?)?;let engine = Engine::new();let session = engine.create(agent);
println!("MODEL: {}", agent::MODEL);demo::run(&session, &question).await?;This engine is in-memory. The agent can explain durable sessions from its corpus, but the example itself does not persist its session.
How the tools work
Section titled “How the tools work”search_docs ranks matches against five bundled pages and returns page IDs, public URLs, and matching excerpts. read_doc accepts only those page IDs and returns the complete snapshot. It never accepts an arbitrary filesystem path.
Validate the behavior
Section titled “Validate the behavior”cargo test -p everruns-framework-support-agentbash examples/everruns-support-agent/demo/record.sh --checkTests cover content-based search, empty and unmatched queries, complete citable reads, arbitrary-path rejection, and interactive input validation. They do not grade the model’s answer; compare a live response with the expected outcome above.
CI runs the offline checks without provider credentials. Live model behavior is evaluated separately.
Demo and recording
Section titled “Demo and recording”Watch the screencast or read the captured transcript to see the tool calls and answer.
With credentials exported and VHS, ffmpeg, and a VHS-compatible browser installed:
bash examples/everruns-support-agent/demo/record.shExport ANTHROPIC_API_KEY before recording. The script updates demo/demo.gif and
demo/transcript.txt after a successful run.
Adapt it
Section titled “Adapt it”Replace the bundled pages with a versioned documentation index while retaining separate search and read operations. Attach source/version metadata, restrict reads to authorized documents, and treat retrieved text as untrusted evidence rather than instructions.
Boundaries
Section titled “Boundaries”The corpus is a five-page snapshot from 2026-09-08, not a live search of the docs site. Provenance is recorded in the corpus README, and the snapshot can lag current APIs.