Industry

Professional Services

Technology for knowledge workers

I build tools for professional services firms-from law to consulting to accounting. I understand the workflow needs of knowledge workers and build systems that enhance rather than replace expertise.

At a glance
Regulations
5 frameworks
KPIs tracked
6 core metrics
Reference stacks
5 patterns
Services
4 engagements
Case studies
0 published
Perspective

How I think about professional services

The architecture, the trade-offs, and where I push back on conventional wisdom.

Professional services - law, accounting, consulting, advisory - runs on two assets: people's time and accumulated judgment. AI in this space isn't about replacing the senior partner; it's about giving every junior associate the leverage of the firm's collective memory. I build tools that compress hours of document review into minutes while keeping the human in charge of the inferences that actually matter.

Retrieval-augmented generation is the foundational pattern. The firm's playbooks, prior memos, contracts, deal precedents, and audit workpapers are the moat - the gold is in the corpus, not the model. I design RAG systems with chunking strategies tuned to document type (clause-level for contracts, section-level for memos), hybrid retrieval combining BM25 and semantic search, and aggressive citation requirements so every generated answer can be traced back to a source paragraph.

Document processing is where the unsexy engineering work lives. PDFs are the world's worst data format, and most legal/finance documents arrive as scans of scans. I build ingestion pipelines using OCR (AWS Textract, Google Document AI, Azure Form Recognizer), layout-aware parsing (Unstructured, Reducto), and entity extraction to turn unstructured filings into queryable records. The extraction quality determines the system's ceiling - bad ingestion makes great retrieval impossible.

Confidentiality is non-negotiable. Attorney-client privilege, audit work-product protections, M&A confidentiality - these aren't compliance checkboxes, they're the foundation of the client relationship. I architect platforms with strict tenant isolation, no cross-firm training, ephemeral context for foundation models, and clear data residency. Increasingly, firms want zero-data-retention agreements with their model providers - Anthropic, OpenAI, and Azure OpenAI all support this, but the architecture has to be designed for it from day one.

The workflow integration is where adoption actually happens. A brilliant AI tool that lives in a separate browser tab dies. The wins come from embedding inside iManage, NetDocuments, Clio, or whatever the practice management system is - generating drafts directly into Word, surfacing comparable clauses inline in the document, pre-filling the time entry from the work product. I help firms architect the integration layer so the AI feels like a natural extension of the tools associates already use. See a legal AI build or reach out to discuss your firm's roadmap.

Challenges

What teams struggle with

The recurring problems I see on professional services engagements.

  • 1Knowledge management and retrieval
  • 2Document processing and analysis
  • 3Billing and time tracking integration
  • 4Client collaboration and portals
  • 5Compliance and confidentiality
How I help

Capabilities I bring

Concrete engineering work that resolves the challenges on the left.

  • AI-powered document analysis
  • Knowledge management systems
  • Client portal development
  • Workflow automation
  • Integration with practice management
Metrics

What teams measure

The KPIs leadership obsesses over in this sector. Most tie back to performance and architecture decisions made years before the dashboard was built.

01

Realization rate

Billed hours as a share of recorded hours; AI-assisted drafting often raises this 5-10 points.

02

Hours per matter

Average effort to close a matter type; the cleanest productivity metric.

03

Time-to-first-draft

Minutes from kickoff to a usable working draft; the user-felt AI win.

04

Citation accuracy

Share of generated outputs whose citations are verified correct; a critical quality bar.

05

Knowledge reuse rate

How often historical work product is found and reused; the moat metric for a firm KM system.

06

Net Promoter Score (client)

Client experience signal increasingly tied to portal and collaboration tooling.

Reference stacks

Stacks I see most often

Patterns I reach for first when scoping a professional servicesengagement. I don't pick technologies for novelty - read more about how I choose.

1

OpenAI / Anthropic + LangChain or LlamaIndex orchestration, with Pinecone or pgvector for retrieval

2

Next.js client portal on Vercel, with Auth0 or WorkOS for client SSO

3

Postgres + S3 for document storage, Textract/Reducto for OCR and layout parsing

4

iManage / NetDocuments / Relativity integrations via REST or Microsoft Graph

5

Snowflake for billable analytics, dbt for transformations, Sigma or Hex for partner reporting

Technologies

Tools of the trade

The platforms and frameworks I lean on for professional services work.

Building for Professional Services?

Let's discuss your specific challenges and how technology can help you ship safely, sleep well, and keep regulators happy.

Command Palette

Search for a command to run...