Research2026-06-10 · source-backed

"Is Grep All You Need?" PwC says reach for grep before vectors, then tune the harness, not the retriever.

Issue

2026-06-10

Confidence

source-backed

Sources

Redaction

passed

Story

The empirical study across Chronos plus the Claude Code, Codex, and Gemini CLI harnesses found literal grep generally beats vector retrieval on LongMemEval fact recovery. The bigger finding: accuracy swings more on which harness and tool-calling style you use than on the retrieval method. The same grep tool even scores differently depending on whether the model reads results inline or from a file. Stop assuming the embedding model is your bottleneck and start A/B testing the harness as a first-class variable.

Source trail

The empirical study

Entities

Chronos Claude Code Codex Gemini CLI LongMemEval PwC

Provenance

Canonical issue: Ramsay Research Agent — June 10, 2026
AI generated: no
Story unit: 2026-06-10-is-grep-all-you-need-pwc-says-reach-for-grep-before-vectors-then-tune-the-harness-not-the-retrie
Labels: source-backed, canonical briefing excerpt

"Is Grep All You Need?" PwC says reach for grep before vectors, then tune the harness, not the retriever.

Story

Related stories

Warp Terminal Goes Open Source at 56,000 Stars. It's Not a Terminal Anymore.

Anthropic Engineers Say Stop Building Agents, Build Skills Instead

HuggingFace Skills (7,500 stars, +5,938/week)

"Write once, run on any agent" becomes the skills bet.

Multi-CLI "cowork" desktop apps are unifying Claude Code, Codex, Gemini CLI, and OpenCode under one runtime.

Code-to-knowledge-graph layers are becoming standard agent onboarding.

cc-switch centralizes keys and config across your coding-agent CLIs.

Give your coding agent LSP-backed symbol retrieval with Serena instead of letting it grep whole files

Source trail

Entities

Provenance