Changelog
What's new in
Product updates, new features, and improvements shipped every week. We build in the open.
July 31, 2026
Daily Prioritized Insight Feed
Connected ERP data now becomes a daily, evidence-backed commercial brief across sales, stock, memo, and margin, with cross-domain relationships and data health kept in view.
NewThe Insight Feed prioritizes up to five commercial items each day, so teams can focus on the signals that matter most.
NewEvery insight states its exact comparison periods and brings together drivers, supporting evidence, history, and clear investigate, save, or dismiss actions.
NewDeterministic detectors and durable episodes make recurring operational signals easier to review and investigate with confidence.
ImprovedSource-readiness checks, restatements, and tenant isolation keep the brief grounded in data that is ready to use and authorized for the viewer.
ImprovedCommercial priorities are scored consistently to make the daily feed easier to scan and act on.
ImprovedThe release is tenant-gated with shadow review and release gates, so teams can validate insight quality before broader access.
ImprovedV1 is limited to the daily feed and investigation workflow: Insight-to-Watch is not part of V1. External notifications and user-configurable detectors are not part of V1.
July 29–30, 2026
Reports Workbench, Conversational Chart Editing & Paper-first UI
Reports are now a more direct, traceable analytical workbench rather than a static output surface, with a refined paper-first experience across the app and marketing site.
NewConversational chart editing turns report-chat requests into typed chart operations with live previews before changes are applied.
NewAnalysts can bind concepts directly, tune chart encodings, and introduce free-text concepts when a report needs a more precise view.
NewPersistent, attributed edit history records what changed, while publish summaries make each report update easier to trace.
ImprovedClear save and revert states, plus hardened report sessions, make longer editing sessions more dependable.
ImprovedCharts now refresh and persist reliably as reports are edited, so the visual analysis remains aligned with the report.
ImprovedSchema-aware column validation keeps chart plans tied to available data and prevents invalid report edits.
ImprovedA premium paper-first design system refresh brings calmer surfaces, clearer hierarchy, and consistent polish to marketing and product workspaces.
July 19–26, 2026
Data Explorer, Governed Semantic Catalogs & Tenant Administration
Teams can now explore operational data in a spreadsheet-style workspace while administrators manage the governed semantic foundations and tenant controls behind it.
NewDataset Explorer provides full-width spreadsheet-style browsing with filters, groups, totals, saved views, and chat prefill for faster investigation.
NewRead-only catalogs make governed metrics and dataset relationships easier to discover before asking analytical questions.
NewAdministrators can manage semantic entities with guided editors for datasets, relationships, metrics, glossary entries, synonyms, and golden questions.
NewA guarded tenant configuration registry centralizes AI models, feature access, and operational limits for each tenant.
ImprovedGrouped team, role, review, and configuration workflows now offer more consistent administration across the product.
ImprovedGoverned-metric linting and semantic validation catch definition issues before they reach analytical workflows.
ImprovedDeprecated-column protection, populated Query Insights, and more reliable RLS and audit handling strengthen safe multi-tenant operations.
July 21–24, 2026
dbt Authoring, Semantic Sync & Pipeline Operations
Data teams can now author and operate dbt models from Lookato, with richer pipeline context and semantic metadata that stays aligned with warehouse work.
NewBrowser-based dbt authoring supports model editing, validation, runs, and Git commits without leaving the data operations workspace.
NewSelective dbt runs expose compiled SQL, Git changes, and commit attribution so operators can understand exactly what ran and changed.
NewSemantic registry metadata can be regenerated and imported from dbt schemas to keep governed analysis aligned with transformed data.
ImprovedA six-tab pipeline detail experience separates operations, data, configuration, and cost context for faster day-to-day pipeline work.
ImprovedIdentity mapping, schema handling, timezone behavior, and missing-record recovery are more reliable across pipeline operations.
ImprovedRoute and concurrency hardening makes dbt execution and pipeline changes safer under active operational use.
July 18–20, 2026
Evidence, Reproducible Evaluation & Flexible Model Infrastructure
Lookato now has a stronger foundation for trustworthy answers: evidence is carried across answer paths, and analytical quality can be tested, reproduced, and released with confidence.
NewEvidence now travels with every answer path, giving analysts stronger provenance for the result they are reviewing.
NewPinned ClickHouse snapshots make reproducible evaluation possible against a stable view of analytical data.
ImprovedHeadless evaluation seams and a baseline runner support repeatable quality checks without relying on the user interface.
ImprovedHermetic conformance, safety-evidence, and release checks strengthen the path from analytical change to production.
NewAn OpenRouter provider abstraction broadens model infrastructure while keeping model selection governed per tenant.
ImprovedMCP and REST now share analytical orchestration and billing behavior, giving integrations the same governed experience as the app.
ImprovedVetted compute operations and safer structured-output handling make complex analytical execution more dependable.
June 17–20, 2026
Lookato Brand and Design-system Overhaul
Lookato now presents a more distinctive, accessible, and consistent experience across the product, administration, marketing, and every customer touchpoint.
ImprovedMode-aware brand tokens and themes bring accessible semantic colours and aligned chart palettes to light and dark experiences.
ImprovedWarm-paper surfaces refresh the admin and app shells, dashboards, login, and navigation with clearer visual hierarchy.
NewA complete brand kit adds responsive logo and mark usage, favicons, PWA assets, brand guidance, and refreshed social imagery.
ImprovedThe redesigned homepage pairs richer product demonstrations with editorial typography and more authentic Gems & Jewellery copy.
ImprovedMobile, accessibility, and SEO polish make the marketing experience clearer and more useful on every screen.
ImprovedConsistent branding now carries through PDFs, exports, emails, invitations, the product app, and administration.
May 19–28, 2026
Reports V1, Memory, Learning & Trust Improvements
This release made analytical work more durable and trustworthy, from report creation and sharing to remembered context, clearer result handling, learning loops, and operational support.
NewReports V1 adds authoring, execution, filters, parameters, summaries, past runs, exports, sharing, and administrative controls.
NewLQL v2 expands analytical expression with window functions, CASE logic, CTEs, cross-step joins, repair rules, rollups, and governed output.
NewDurable conversation memory carries relevant context forward so analytical discussions do not have to restart each time.
ImprovedResult-shape heuristics, sample-data mode, first-login guidance, and WHERE-value validation make early exploration easier and safer.
ImprovedTrust tiers, learning events, clarification promotion, attribution, and review workflows make the system easier to improve with confidence.
NewIn-app help and actionable support links give teams a direct path when they need guidance or follow-up.
FixedSurfaced failures, security hardening, and CI stabilization make everyday analytical work more reliable.
May 2026
Lookato G&J — Operations intelligence for the Gems & Jewellery industry
We've focused Lookato on what we do best: helping diamond and jewellery manufacturers run their operations with real-time visibility, governed metrics, and proof for every answer. New dedicated product page, 5 industry-specific use case pages, events page for IIJS Mumbai, and a complete website repositioning for the G&J industry.
NewLookato G&J product page — detailed walkthrough of conversational queries, evidence pane, governed metrics, pre-built dashboards, and ERP integration for diamond and jewellery operations.
New5 industry-specific use case pages: diamond manufacturing, jewellery manufacturing, diamond trading, lab-grown diamond, and integrated houses. Each with real operational questions and dashboard previews.
NewAbout page — our story in Surat building Trybe, Ornix, and DiaDNA for the Gems & Jewellery industry.
NewEvents page — meet us at IIJS Mumbai (August 2026), Hong Kong Jewellery Fair (September), and Vicenzaoro (September).
NewQualified demo request form with G&J-specific fields: business type, current ERP systems, company size.
ImprovedComplete website repositioning: homepage, features, how-it-works, pricing, security, navigation, and footer — all rewritten for Gems & Jewellery operations.
May 8, 2026
Governed Analytics, Evidence Pane & Semantic CI
The trust update. Every answer now carries provenance — which governed metric was used, which formula was applied, and whether the plan was validated. Plus golden question regression suites that catch governance drift before users do.
NewGoverned Metrics Layer — define metrics with exact formulas (definition_json), compiled deterministically to LQL expressions. Three-step enforcement: resolve metric from query, inject into planner prompt, validate the generated plan. Published metrics are versioned with approval workflow.
NewEvidence Pane — every answer shows a collapsible provenance panel: governed metric name + version, formula used, dataset, freshness, match type (exact/alias/semantic), and validation status. Business View for all users; Analyst View (SQL, compiled expression, LQL plan) for admin/analyst roles. Analyst-only fields redacted server-side.
NewGolden Questions + Semantic CI — register golden questions with approved baselines. Run on-demand regression suites that compare responses against baselines. Drift comparator checks: dataset, governed metric presence (by ID), compiled formula, dimensions, filters, query path. Catches governance drift from prompt changes, model upgrades, or glossary edits.
NewDeterministic metric compiler — definition_json compiles to dialect-neutral LQL expressions (ratio, aggregation, filtered_count). The LLM selects the metric; the compiler constructs the exact formula. No hand-authored governed calculations.
NewGoverned metric ambiguity clarification — when multiple governed metrics match (e.g., "margin" matches both Gross Margin % and Net Margin), the system presents clickable pill buttons for disambiguation instead of guessing.
NewAdmin metrics management page — CRUD for governed metrics with versioning, aliases, status lifecycle (draft → staging → published → archived), and audit logging. Admin golden questions page with baseline review, suite execution, and drift results.
New15 seed golden questions for diamond trading — including adversarial synonym tests ("What is profit margin?" → should resolve to governed Gross Margin %). Slug-to-ID resolution ensures stable test references.
ImprovedEvidence persisted with every assistant message — reopening conversations renders stored evidence snapshot, not regenerated data. Evidence survives across sessions.
FixedFixed analytical orchestrator fallback: governed metric validation failures and ambiguity clarifications no longer silently fall through to single-shot path.
FixedFixed ClarificationCard styling for dark theme — replaced CSS variable styling with Tailwind classes for reliable rendering.
April 24, 2026
Conversational Intelligence, Admin Glossary & Exports
The biggest update yet. A multi-layer AI intelligence system that understands your business terms, asks when unsure, and guides exploration. Plus admin glossary management and CSV exports.
NewConversational Intelligence — multi-layer intent resolution with nano classification (GPT-5.4-nano), full resolution (GPT-5.4-mini), and binding constraints to the query planner
NewSmart Clarification — ClarificationCard UI with clickable options when terms are ambiguous. Structured API responses for reliable selection.
NewBusiness Glossary with ambiguity flags — define ambiguous terms with multiple interpretations. Managed via admin UI, no SQL required.
NewSmart follow-ups — data-aware suggestion chips generated from actual query results, not generic prompts
NewCoaching banner — progressive reveal showing intent, confidence, and assumptions while you wait for results
NewPost-execution LLM narrative — GPT-5.4-mini generates contextual narratives in parallel with deterministic fallback
NewPDF sharing with conversation context — prior Q&A pairs shown above the shared answer for full context
NewAdmin glossary management page — table view, add/edit modal with translation templates, delete confirmation
NewAdmin exports page — CSV export with sync download (< 10K rows) or async job tracking with polling
NewDomain guidance — enriched dataset domainContext in planner prompt replaces YAML playbooks
ImprovedGPT-5.4 model upgrade — centralized model config with env var overrides, all LLM call sites migrated
ImprovedQuery latency optimization — removed redundant LLM call (2-5s savings), parallelized orchestrator setup, eliminated duplicate data fetches, granular SSE status updates
ImprovedIntent resolver parser made tolerant of LLM output variations — accepts missing optional fields, coerces types
FixedFuzzy resolver below-threshold bug — candidates from ClickHouse that scored below threshold now trigger clarification instead of silent no-match
FixedInvalid resolvedMetrics/breakdownDimensions filtered against dataset schema before reaching planner
FixedcountIf without field auto-corrected to count instead of validation error
FixedPie/donut chart blocked for single-category data — falls through to bar chart
FixedClarification response JSON no longer shows as raw text in chat bubbles or exported PDFs
March 31, 2026
Live Dashboards, Chat-to-Notebook & PDF Sharing
Pin insights to live dashboards, save analyses to notebooks, and share any answer as a beautifully formatted PDF.
NewLive dashboards — pin any chat answer to a dashboard card with auto-refresh
NewChat-to-notebook — save any analysis to a collaborative notebook with one click
NewPer-answer PDF export — beautifully formatted A4 PDF with header, narrative, charts, tables, and metrics
ImprovedQuery inspector — see the SQL, execution stats, and step details behind any answer
March 23, 2026
Watches & Alerts System
Monitor any metric with scheduled watches. Get notified via Slack or email when thresholds are crossed.
NewWatches — schedule recurring queries with threshold alerts
NewAlert delivery via Slack and email with investigation links
ImprovedWatch management page with status tracking, mute/unmute, and history
March 19, 2026
Premium Chat UX & Visual Polish
Redesigned chat experience with premium pipeline rendering, key insights, confidence indicators, and follow-up chips.
NewPremium pipeline — structured rendering with key insight headline, confidence badge, metric cards, charts, tables, follow-up chips
ImprovedTypography and visual hierarchy overhaul across the chat interface
See Lookato G&J in action with your data.
Book a 30-minute demo with someone who knows the Gems & Jewellery industry.
By the makers of Trybe and Ornix · Founded in Surat, the world's diamond capital