Metasense V2: Enhancing, improving and productionisation of LLM powered data governance

Summary

Grab scaled Metasense to automate metadata generation, column-level classification, and sensitivity tiering across its entire data lake. Post-rollout analysis revealed that high tag volumes, wide tables, and mixed content—such as nested JSON and customer communications—strained model capacity and led to missed Personally Identifiable Information (PII). To overcome these limitations, the team split the classification process into distinct PII and non-PII tasks, reduced prompt word counts, and partitioned tables with over 150 columns into smaller units. Integrating LangChain and LangSmith modernized the architecture by enabling direct prompt experimentation, custom metric tracking, and version-controlled deployments. The updated pipeline achieved low misclassification rates alongside automated alert thresholds to trigger model improvement protocols if errors increase.

Takeaways

• To resolve capacity constraints caused by having 13 non-PII tags among 21 total tags, the model was split into two separate parts: one dedicating 8 tags strictly to PII and another handling non-PII.
• Prompt engineering optimizations reduced prompt length from 1,254 words to 737 words, while wide tables exceeding 150 columns were divided into smaller tables to maintain LLM focus per column.
• The backend integrated LangChain for component chaining and LangSmith to manage evaluation datasets, track latency and error rates, and deploy prompt template updates via configuration identifiers.

Related reading

• Grab · Oct 23, 2024

  LLM-assisted vector similarity search

  Vector similarity search often struggles with conceptual nuances, negations, and complex constraints despite its efficiency in high-dimensional semantic retrieval. To address this limitation, a two-step retrieval pipeline combines Facebook AI Similarity Search (FAISS) using OpenAI's text-embedding-ada-002 embeddings with a large language model re-ranking step powered by GPT-4o. The initial FAISS search extracts a candidate shortlist of matches, which GPT-4o then re-ranks based on contextual relevance and query intent. Evaluations on structured datasets showed that while simple queries yielded comparable results across methods, the LLM-assisted approach effectively resolved negations and conceptual matching where raw vector search failed. Internal production trials on relational datasets exceeding 4,500 rows demonstrated similar relevance improvements, with additional query latency being the primary operational trade-off.

  Md Riyadh

• Grab · Dec 12, 2024

  Turbocharging GrabUnlimited with Temporal

  GrabUnlimited experienced scaling bottlenecks, corrupted membership states, and elevated production incidents after its subscriber base grew by over 1000%. The original architecture relied on Amazon SQS state machines, 5-minute Redis locks, and daily batch cron jobs that overwhelmed the database and lacked granular idempotency during upstream retries. To eliminate these failure modes, the engineering team migrated the core membership lifecycle to Temporal's workflow orchestration engine. Replacing batch cron jobs with Temporal Timers distributed renewal operations throughout the day, while matching workflow IDs prevented race conditions between renewals and cancellations. This architectural transition resolved database bottlenecks and yielded an 80% reduction in open production incidents.

  Michel Parreno

• Grab · Oct 30, 2024

  How we reduced peak memory and CPU usage of the product configuration management SDK

  Grab's central product configuration management platform, GrabX, previously aggregated all configurations across every backend service into a single JSON file hosted on AWS S3. Every minute, client SDKs fetched, parsed, and loaded this growing file—which exceeded 100MB—causing CPU throttling spikes, elevated P99 latency, and unnecessary memory consumption. Analysis revealed that 98% of services required less than 1% of the total configuration data. To resolve these bottlenecks, the team partitioned data by service, split configurations into separate S3 files under distinct prefixes, and introduced a per-service changelog for incremental updates. Benchmarks showed the redesign decreased maximum CPU utilisation by over 50% and reduced memory usage by up to 70%.

  Ram Dilip Pradhan

• Grab · Sep 26, 2024

  Enabling conversational data discovery with LLMs at Grab

  Grab faced major bottlenecks in dataset discovery across its 200,000 data lake tables due to low documentation coverage and vanilla Elasticsearch limitations in its internal tool, Hubble. To resolve this, engineers first tuned Elasticsearch by boosting frequently queried P80 tables and certified schemas while deboosting deprecated datasets. They then deployed a GPT-4 pipeline that generated documentation from table schemas and sample data, raising P80 documentation coverage from 20% to roughly 90%. Finally, the team developed HubbleIQ, an LLM-powered assistant built via Glean Apps and integrated into Slack and Hubble search to answer semantic queries. These initiatives increased search click-through rates to 94% and lifted the proportion of users finding discovery easy to 73%.

  Shreyas Parbat