Repository navigation
feat(evaluate): add TypeScript HR assistant agent evaluation sample - #2165
Open
BharathiSrini wants to merge 1 commit into
Open
BharathiSrini wants to merge 1 commit into
BharathiSrini wants to merge 1 commit into
Conversation
mvangara10
previously approved these changes
Oct 7, 2026
|
Latest scan for commit: Security Scan Results |
BharathiSrini
force-pushed
the
typescript_agents
branch
2 times, most recently
from
October 9, 2026 19:45
d54599e to
3893e90
Compare
Demonstrates the full AgentCore Evaluations lifecycle for a LangGraph TypeScript agent deployed as a custom container on AgentCore Runtime: on-demand (EvaluationClient), dataset (OnDemandEvaluationDatasetRunner), batch (StartBatchEvaluation) and online (CreateOnlineEvaluationConfig). - agent.ts: stamp ADOT-style resource attributes (service.name, cloud.resource_id, ...) on exported span docs so batch and online evaluation can discover sessions; strip Nova <thinking> tags; remove unused helpers and dependencies - deploy.py: inject OTEL_LOG_GROUP_NAME, OTEL_SERVICE_NAME and AGENT_RUNTIME_ARN after runtime creation; refactor into functions - evaluate.py: restructure into per-stage functions with --modes and --session-id; add 4-scenario ground-truth dataset; scope batch jobs to the run's session IDs; move HRPolicyAccuracy to the dataset stage (plain-string expected_response only covers the last trace) - cleanup.py: delete batch evaluations, online configs and their results log groups, evaluators, the runtime and its log group, ECR repository and IAM roles recorded in results/cleanup_state.json; safe to re-run - READMEs: document the lifecycle, per-stage evaluators and results - Pass ruff check/format and pylint (10.00/10)
BharathiSrini
force-pushed
the
typescript_agents
branch
from
October 9, 2026 20:12
3893e90 to
a525a3d
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Introduces a complete evaluation workflow for a TypeScript-based HR assistant agent running in AgentCore Runtime:
Amazon Bedrock AgentCore Samples Pull Request
Important
review readylabel to it. Only PRs withreview readywill be reviewed.Issue number:
Concise description of the PR
Evaluations on agents that are developed using TypeScript
User experience
Checklist
If your change doesn't seem to apply, please leave them unchecked.
Acknowledgment
By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of the project license.