How we used DSPy to turn AI evaluations into better responses in Dash chat

Summary

Dropbox improved its Dash chat agent by establishing an automated optimization loop powered by DSPy and LLM-as-judge evaluations. Engineers first calibrated their LLM judges against human-annotated interaction traces, then used those judges to systematically optimize the agent's system prompts via offline counterfactual replay. This automated workflow reduced incomplete responses by 26% while decreasing overall token consumption.

Takeaways

• Agent evaluation requires scoring multi-step execution trajectories—including intent recognition, tool selection, and grounding—using structured failure codes and reasoning notes rather than just judging final outputs.
• A two-stage DSPy optimization pipeline can first calibrate LLM judges against human ratings (using algorithms like GEPA and MIPROv2) and then use those calibrated judges to optimize the agent's prompt.
• Automating prompt optimization with offline counterfactual replays doubled experimentation velocity, reduced incomplete answers by 26%, and cut overall token usage by 5.4%.

Related reading

• Dropbox · Mar 17, 2026

  How we optimized Dash's relevance judge with DSPy

  Dropbox Dash optimized its LLM-as-a-judge relevance scoring system using DSPy to migrate from expensive proprietary models to cheaper open-weight alternatives. By establishing automated feedback loops based on human agreement and strict JSON format validation, the team systematically generated robust prompts for new models. This reduced human-score disagreement by 45% and slashed model adaptation time from weeks to days while enabling 10x to 100x more data labeling.

  Ilya Yakovlev,Andrew Cheung,Binoy Dash,Simran Jumani,Dmitriy Meyerzon,Mark Breitenbach,Ishan Mishra,Kazuaki Okumura,Mike White,Kevin Altschuler,Facundo Agriel,Ishan Mishra,Eric Wang,Dmitriy Meyerzon

• Dropbox · Feb 26, 2026

  Using LLMs to amplify human labeling and improve Dash search relevance

  Dropbox Dash uses large language models (LLMs) to amplify human labeling efforts for training its search relevance and ranking models. By validating and optimizing LLM evaluators against a small set of human-labeled internal data, Dropbox creates massive, high-quality training datasets offline for production rankers like XGBoost without incurring high latency or latency costs at query time.

  Ilya Yakovlev,Andrew Cheung,Binoy Dash,Simran Jumani,Dmitriy Meyerzon,Mark Breitenbach,Ishan Mishra,Kazuaki Okumura,Mike White,Kevin Altschuler,Facundo Agriel,Ishan Mishra,Eric Wang,Dmitriy Meyerzon,Dmitriy Meyerzon

• Salesforce · Aug 17, 2026

  How to Evaluate Production AI Agents: Measure System Outcomes, Not Conversations

  Evaluating AI agents solely on conversational transcripts fails when agents must invoke tools to modify external production systems. Language models can convincingly narrate that an action occurred while completely omitting the underlying tool call, leaving database or billing records unchanged. Outcome-based evaluation addresses this divergence by treating external system mutations rather than generated dialogue as the actual source of truth. Frameworks such as CRMAgentBench implement persistent, stateful environments with strict all-or-nothing validation, verifying tool arguments, execution sequence, final record modifications, and the total absence of unauthorized actions. Furthermore, measuring repeated success across independent executions using pass^k metrics exposes operational variance and inconsistency that standard single-shot scores and pass@k metrics conceal.

  Scott Nyberg

• Grab · Jul 15, 2024

  LLM-powered data classification for data entities at scale

  Grab needed to classify sensitive data at the table and column level across petabytes of database tables and streaming schemas. Manual schema-tiering campaigns had resulted in half of all schemas receiving overly strict Tier 1 access controls, while an initial automated service using regex patterns and third-party machine learning produced high false-positive rates and lacked customizability. To address this, the Caspian data engineering and governance teams enhanced their internal orchestration service, Gemini, by integrating GPT-3.5 via Azure OpenAI. Gemini aggregates classification requests into mini-batches, handles API rate limits, and uses prompt engineering—including few-shot examples, curated tag libraries, and explicit JSON DTO schemas—to reliably tag columns for data owner verification.

  Hualin Liu