---
title: 1.5 months to 1.5 minutes · Reference Case · Zero Fog
description: A top-tier strategy firm needed faster intelligence without losing partner-grade depth. A structured mirror and domain-tuned synthesis cut 6 weeks to minutes.
image: https://www.zero-fog.com/hubfs/zf-share-selected-work.png
---

[![Zero Fog](https://www.zero-fog.com/hubfs/Zero-fog-site/zero-fog-logo.png)](https://www.zero-fog.com/?hsLang=en)

[How we work](https://www.zero-fog.com/how-we-work?hsLang=en) [Situations](https://www.zero-fog.com/situations?hsLang=en) [Selected work](https://www.zero-fog.com/reference-cases?hsLang=en) [Perspectives](https://www.zero-fog.com/insights?hsLang=en) [About](https://www.zero-fog.com/about?hsLang=en) [Talk to us](https://www.zero-fog.com/contact?hsLang=en)

Selected work · 04 of 09

# 3 months → 1.5 minutes — without losing depth.

**The Situation:** A top-tier strategy and advisory organization needed to dramatically accelerate how its client-facing leaders produced strategic, financial, and competitive intelligence. The existing cycle — synthesizing earnings calls, filings, competitive shifts, and internal materials into partner-ready output — required roughly three months. Generic GPT experiments produced faster results that the partners couldn't trust.

The Constraint We Identified

## Speed was the obvious problem. Depth was the actual one.

Every advisory organization in the world was running the same experiment in the same year: pointing a generic large language model at a stack of public-company documents and seeing if useful output came out the other side. It usually didn't, in the sense that the output sounded plausible and didn't quite hold up under scrutiny. Partners who had spent careers building strategic judgment could tell within a paragraph that the synthesis was shallow, even when they couldn't immediately name what was missing.

The actual constraint was not the LLM. It was the absence of a structured context the LLM could reason against. A model asked to summarize an earnings call produces a summary. A model asked to interpret an earnings call against a structured representation of the company's strategic position, its competitive set, and its KPI trajectory produces something closer to analysis. The difference is the model underneath.

What We Built

## A structured model of the relevant companies and KPIs, with a domain-tuned synthesis layer on top.

Structural pattern Cycle-time collapse

CYCLE TIME — PARTNER-READY STRATEGIC INTELLIGENCE BEFORE Manual synthesis ~3 months Gather Read Synthesize Draft Review APPLIED AI SYNTHESIS · STRUCTURED MODEL AFTER Automated ~1.5 minutes Same depth, structured context, confidence-qualified

**The structural pattern.** Cycle-time collapse is the headline metric. The real change is underneath: a structured representation of the companies, KPIs, and competitive context that allows the synthesis layer to reason rather than summarize.

- **Map**We built investment-grade structured representations of the companies in scope — KPIs, strategic drivers, competitive position, regulatory context. Automated ingestion pipelines kept the model current from earnings transcripts, filings, and internal analysis. The model became the single source of truth that downstream synthesis could reason against.
- **Assess**The relevant constraint was the firm's ability to convert raw inputs into senior-decision-grade analysis at velocity. Generic GPT had improved speed at the cost of depth; the design challenge was preserving depth while collapsing time.
- **Decide**We engineered an applied AI synthesis layer specifically calibrated to the firm's strategic frameworks. Every output carried confidence qualification — a feature that turned out to be the deciding factor for partner adoption. Partners trusted output that told them where it was confident and where it wasn't.
- **Execute**Quarterly cycles tuned the synthesis against real partner feedback. Adoption spread organically once a handful of senior partners saw the depth held up. By the end of year one, the system was the firm's standard pre-call preparation engine.

What the Engagement Produced

## The synthesis layer is now part of the practice.

~3 mo → ~1.5 min

Strategic intelligence cycle

For partner-ready output. Depth and accuracy improved relative to the manual baseline.

+11% YoY

Commercial growth

In the supported commercial group. Engagement contributed; multiple drivers.

Global

Adoption

Standardized across regions and practice areas within twelve months of pilot.

The cycle-time number is the cleanest single read. The 11% commercial growth was a contributory outcome — the synthesis system supported commercial conversations the firm would not have been able to have at that quality and timing without it, but the growth had multiple drivers and we don't claim sole attribution. The adoption metric matters most for the methodological lineage: this is the engagement where applied AI synthesis became a repeatable practice, not just a one-off build.

### What carried forward into Zero Fog's work today

A structured model as the foundation for analysis, and stated confidence on every output. Every finding in an engagement today carries its evidence.

### Facing a similar decision?

Zero Fog Advisory Group · quarterly execution cycles · founder-led

[Talk to us](https://www.zero-fog.com/contact?hsLang=en)

More selected work

#### [03 · Institutional sales & research The right idea, to the right desk, at the right moment.](https://www.zero-fog.com/reference-cases/institutional-sales-intelligence?hsLang=en)

#### [07 · Bank digital personalization Personalization for 60 million clients, one journey at a time.](https://www.zero-fog.com/reference-cases/bank-digital-personalization?hsLang=en)

#### [08 · Digital capital allocation One basis for every digital dollar.](https://www.zero-fog.com/reference-cases/digital-capital-allocation?hsLang=en)

[![Zero Fog](https://www.zero-fog.com/hubfs/Zero-fog-site/Transparent%20Logo_white%20logo%20side.png)](https://www.zero-fog.com/?hsLang=en)

Founder-led advisory for consequential decisions.

Site

[How we work](https://www.zero-fog.com/how-we-work?hsLang=en)  
[Situations](https://www.zero-fog.com/situations?hsLang=en)  
[Selected work](https://www.zero-fog.com/reference-cases?hsLang=en)  
[Perspectives](https://www.zero-fog.com/insights?hsLang=en)  
[About](https://www.zero-fog.com/about?hsLang=en)

More

[Partners](https://www.zero-fog.com/partners?hsLang=en)  
[Rejoyce](https://www.rejoyce.ai)  
[Talk to us](https://www.zero-fog.com/contact?hsLang=en)

Contact

hello@zero-fog.com

 © 2026 Zero Fog, LLC. All rights reserved. · Massachusetts, USA

[Privacy](https://www.zero-fog.com/privacy?hsLang=en) · [Terms](https://www.zero-fog.com/terms?hsLang=en) · [LinkedIn](https://www.linkedin.com/company/zero-fog)