Delivered, with the numbers on it.

Six Thinkscoop engagements that shipped, read here as engineering problems rather than as logos. The figures are the ones the clients agreed to publish, and every page says which discipline the engagement is actually evidence of.

EY (Ernst & Young)

72%reduction in report preparation time

A multi-agent AI system operating entirely within EY's Azure environment that ingests audit data, cross-references regulatory frameworks, and generates source-cited draft reports for human partner review.

Professional Services · 12 weeks

Booking.com

68%queries resolved without human intervention

A LangGraph reasoning agent with live access to booking APIs, a RAG knowledge base over 500,000+ policy documents, and direct payment system integration - with confidence-based escalation that assembles full context for human agents before routing.

Travel & eCommerce · 10 weeks

Global FinTech (Confidential)

78%reduction in processing time

A multi-step LangGraph reconciliation agent that reasons over discrepancy reports, queries source systems via API, and drafts resolution actions for human review - with a full evaluation harness measuring accuracy and escalation rate weekly.

Financial Services · 10 weeks

Hindustan Unilever Limited

4.2minavg query resolution (was 2 days)

A unified AI knowledge assistant with RAG over 200,000+ internal documents, role-based access control tied to SSO, full audit logging, and citation-grounded answers - operating entirely within HUL's Azure environment.

FMCG / Enterprise · 14 weeks

SAMCo

3×faster portfolio risk analysis

A real-time portfolio intelligence platform with live market data feeds, AI risk modelling, and a natural language query interface - so managers get cited answers to risk exposure questions in seconds, not a day later.

Financial Services · 8 weeks

Pixis

35%reduction in ad spend wastage

A multi-touch attribution engine with AI-assisted causal inference, processing 5M+ events daily across Google, Meta, and TikTok - giving marketing teams a defensible, explainable model for budget decisions.

MarTech / AI Marketing · 6 weeks

engineering / what each one is evidence of

The engineering problem underneath.

A case study is easy to read as a sector. It is more useful read as a constraint, because the constraint is the thing that transfers to your build.

72%EY (Ernst & Young)Citation first output in a regulated setting, inside the client's own cloud tenancy, with confidence routing to a named human reviewer and an immutable record behind every claim. This is the evaluation and guardrails problem at its strictest, because the reader is a partner signing their name to it.12 weeks · Professional Services 68%Booking.comRetrieval over a very large policy corpus where the correct answer depends on the version of a policy in force on the booking date, not the current one. The escalation surface was designed before the resolution path, which is the design decision the whole engagement turns on.10 weeks · Travel & eCommerce 78%Global FinTech (Confidential)An agent with authority to act across finance systems, which is the hardest version of the authority problem: writes have to be idempotent, thresholds have to be enforced in code, and every decision has to survive a question asked months later.10 weeks · Financial Services 4.2minHindustan Unilever LimitedRetrieval across the systems a large organisation actually keeps its knowledge in, with access control following the document into the index. At this scale the engineering risk is permissions and freshness rather than reasoning.14 weeks · FMCG / Enterprise 3×SAMCoReal time data engineering under a latency budget in a regulated market, where the numbers have to reconcile against the source before anyone will act on them. Mostly a platform problem, which is what most production AI turns out to be.8 weeks · Financial Services 35%PixisModelling across fragmented sources where the output changes budget decisions, so the pipeline, the reproducibility and the ability to explain a number matter more than the sophistication of the model.6 weeks · MarTech / AI Marketing

None of these is your problem exactly.

Send yours. What transfers between engagements is the constraint, not the sector, and the first useful thing we can tell you is which of these it most resembles.

Start a build