Quality assurance · Production

Leidos uses Sourcegraph Cody to accelerate software development and cut senior developer mentoring time

The problem

Leidos needed an AI coding assistant that met the highest security standards for government and defense clients, avoided LLM lock-in as the field rapidly evolved, and could retrieve context from entire code repositories rather than just the currently open editor tab.

First attempt

Many evaluated alternative coding assistants were eliminated for insufficient security and privacy controls, and their context retrieval was limited to only the open editor tab rather than full repositories.

Workflow diagram · grounded in source
1
Engineer invokes Cody
trigger
“I use Cody every day, all day long”
2
Context retrieval from repos
ai_action
“the context many AI coding assistants pulled from was very limited. For the most part, it was your open tab in the editor, and that was it. But when you're working on a software development project of any type that's even slightly more c…”
3
Code and documentation generation
ai_action
“saving time writing documentation for their code, generating boilerplate in seconds, writing unit tests with unparalleled ease which in turn improves code quality, and debugging significantly faster than before”
4
Legacy migration acceleration
ai_action
“migrating from Oracle to PostgreSQL once took a full sprint, if not longer. Cody got them 80% to 90% of the way there within minutes”
5
Mentoring time reduction
feedback_loop
“Guiding junior developers used to take up about eight hours of the week, easily. With Cody, they've cut this down to two”
Reported outcome

Cody accelerated Oracle-to-PostgreSQL migrations to 80% to 90% complete within minutes, and senior developers reduced time guiding junior developers from about eight hours of the week to two.
Engineers also save time writing documentation, generate boilerplate in seconds, and debug significantly faster.

Reported metrics
Oracle-to-PostgreSQL migration completion80% to 90%
Senior developer mentoring time per weekeight hours of the week... cut this down to two
Documentation timesaving time writing documentation for their code
Boilerplate generation timegenerating boilerplate in seconds
Show all 5 reported metrics
Oracle-to-PostgreSQL migration completion80% to 90%
Senior developer mentoring time per weekeight hours of the week... cut this down to two
Documentation timesaving time writing documentation for their code
Boilerplate generation timegenerating boilerplate in seconds
Debugging speeddebugging significantly faster than before
Reported stack
CodySourcegraph
Source
https://sourcegraph.com/case-studies/cody-leidos-maximizing-efficiency-heightened-security-ai-race
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

Cody accelerated Oracle-to-PostgreSQL migrations to 80% to 90% complete within minutes, and senior developers reduced time guiding junior developers from about eight hours of the week to two.

What tools did this team use?

Cody, Sourcegraph.

What results were reported?

Oracle-to-PostgreSQL migration completion: 80% to 90%; Senior developer mentoring time per week: eight hours of the week... cut this down to two; Documentation time: saving time writing documentation for their code; Boilerplate generation time: generating boilerplate in seconds (source-reported, not independently verified).

What failed first in this deployment?

Many evaluated alternative coding assistants were eliminated for insufficient security and privacy controls, and their context retrieval was limited to only the open editor tab rather than full repositories.

How is this quality assurance AI workflow structured?

Engineer invokes Cody → Context retrieval from repos → Code and documentation generation → Legacy migration acceleration → Mentoring time reduction.

Related quality assurance cases