docs(cookbook): Falcon AI, Agent Command Center, MCP, and Evaluation cookbooks#632
Merged
Conversation
added 8 commits
May 5, 2026 03:45
NVJKKartik
requested changes
May 5, 2026
Contributor
NVJKKartik
left a comment
There was a problem hiding this comment.
Content Looks Good, Please test the code before publishing
| config = agentcc.GatewayConfig( | ||
| load_balance=agentcc.LoadBalanceConfig( | ||
| strategy="weighted", | ||
| targets=[ |
Contributor
There was a problem hiding this comment.
use latest models not these
| import agentcc | ||
| from openai import OpenAI | ||
|
|
||
| config = agentcc.GatewayConfig( |
Contributor
There was a problem hiding this comment.
are you sure this is possible and correct code, please test.... This feature can be displayed in UI
| agentcc.LoadBalanceTarget(model="claude-3-5-sonnet-20241022", provider="anthropic", weight=0.3), | ||
| ], | ||
| ), | ||
| fallback=agentcc.FallbackConfig( |
Contributor
There was a problem hiding this comment.
explain the concepts what is fallback, load_balance etc like one liner and maybe refer to docs
| response = client.chat.completions.with_raw_response.create( | ||
| model="gpt-4o-mini", | ||
| messages=[{"role": "user", "content": "Hello"}], | ||
| ) |
Contributor
There was a problem hiding this comment.
This code looks wrong as you are using openai client, maybe replace it with curl
|
|
||
| r = client.chat.completions.with_raw_response.create( | ||
| model="gpt-4o-mini", | ||
| messages=[{"role": "user", "content": "What is your return policy?"}], |
Contributor
There was a problem hiding this comment.
same as before change the model names, also code looks wrong again....
| "config": {"model": "turing_flash"}, | ||
| }, | ||
| ) | ||
| print(resp.json()) # {"eval_template_id": "...", "name": "support_reply_quality_v1"} |
Contributor
There was a problem hiding this comment.
describe what the response wil look like
added 2 commits
May 5, 2026 14:43
- semantic-caching: add Install intro line, remove em/en dashes - mcp/debug-traces-from-ide: remove em dashes - evaluation/eval-correction-loop: document full create_custom_evals response shape - astro.config.mjs: add server.allowedHosts so ngrok/cloudflare/localtunnel domains work in dev - nav: drop fallback-and-weighted-routing entry; remove the page from this PR (kept locally for later)
NVJKKartik
approved these changes
May 5, 2026
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
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.
Summary
Adds six new cookbook pages covering Falcon AI workflows, Agent Command Center features, MCP-based trace debugging from the IDE, and a domain-calibrated eval workflow. Adds three new cookbook navigation groups (Falcon AI, Agent Command Center, MCP Server, Evaluation) under the existing cookbook tab.
New pages:
cookbook/falcon-ai/end-to-end- full Falcon AI lifecycle (trace, debug, evaluate, dataset, fix) in one chatcookbook/falcon-ai/context-aware-debugging- paste-ready prompt fix in three Falcon AI turnscookbook/falcon-ai/eval-datasets-from-traces- curate eval datasets from production tracescookbook/command-center/fallback-and-weighted-routing- weighted routing + provider failover viaagentcc.GatewayConfigcookbook/command-center/semantic-caching- exact and semantic caching at the gatewaycookbook/mcp/debug-traces-from-ide- connect FAGI MCP server to Cursor/Claude Code/VS Code/etc.cookbook/evaluation/eval-correction-loop- teach an evaluator domain rules via custom eval + few-shot correctionsVerified each cookbook's code against the actual SDK source (agentcc gateway, ai-evaluation, futureagi MCP tools registry) and against the live dashboard for screenshots.
Test plan
/docs/cookbook/quickstart/manual-tracing,/docs/command-center/features/*) for 404s🤖 Generated with Claude Code