DEV Community

Conor Bronsdon profile picture

Conor Bronsdon

Host of Chain of Thought, a technical AI podcast. I build open-source agent tooling and write about what works when you put AI agents into production.

Location Seattle, WA Joined Joined on  Personal website https://chainofthought.show twitter website

Work

Host, Chain of Thought podcast

2 Week Community Wellness Streak
1 Week Community Wellness Streak
Five Year Club
Four Year Club
Three Year Club
Writing Debut
Two Year Club
One Year Club
16 Week Writing Streak
8 Week Writing Streak
4 Week Writing Streak
Let your LLM say I don't know instead of guessing

Let your LLM say I don't know instead of guessing

Comments
4 min read

Want to connect with Conor Bronsdon?

Create an account to connect with Conor Bronsdon. You can also sign in below to proceed if you already have an account.

Already have an account? Sign in
Five lessons for getting enterprise AI past the pilot phase

Five lessons for getting enterprise AI past the pilot phase

1
Comments
4 min read
Price a coding call, then pick the model tier

Price a coding call, then pick the model tier

1
Comments
5 min read
Count transcript tags in a podcast RSS feed

Count transcript tags in a podcast RSS feed

Comments
5 min read
Four agent metrics that a final accuracy score hides

Four agent metrics that a final accuracy score hides

Comments
6 min read
What to change when agents write most of the code

What to change when agents write most of the code

Comments
5 min read
The Minimum Agent Loop You Can Ship (and When to Skip It)

The Minimum Agent Loop You Can Ship (and When to Skip It)

2
Comments 2
4 min read
Measure an AI agent before you call it ready to ship

Measure an AI agent before you call it ready to ship

Comments
4 min read
Lint your technical drafts for AI writing tells before you publish

Lint your technical drafts for AI writing tells before you publish

Comments 1
4 min read
Ship AI features inside a hard latency budget

Ship AI features inside a hard latency budget

Comments
5 min read
When a support assistant should hand off to a person

When a support assistant should hand off to a person

Comments
5 min read
Count tokens before you ship so agent bills do not surprise you

Count tokens before you ship so agent bills do not surprise you

Comments
4 min read
Plan inference capacity before an agent feature ships

Plan inference capacity before an agent feature ships

1
Comments
5 min read
Allow-list MCP servers before a company-wide rollout

Allow-list MCP servers before a company-wide rollout

Comments
5 min read
Dependency hygiene when exploits land in weeks

Dependency hygiene when exploits land in weeks

Comments
6 min read
Review the boundary, not every line

Review the boundary, not every line

1
Comments 1
6 min read
A pre-flight checklist before domain continued pre-training

A pre-flight checklist before domain continued pre-training

Comments
5 min read
Five questions to ask before you trust an AI feature's eval score

Five questions to ask before you trust an AI feature's eval score

Comments
5 min read
Audit your week when agents write the code

Audit your week when agents write the code

1
Comments
5 min read
Design four tables before you write the agent

Design four tables before you write the agent

Comments
4 min read
Map your AI stack by layer before you pick vendors

Map your AI stack by layer before you pick vendors

Comments
4 min read
When to fine-tune a small model for one narrow task

When to fine-tune a small model for one narrow task

Comments
6 min read
What to alert on when your LLM feature is live

What to alert on when your LLM feature is live

2
Comments 2
5 min read
Choose in-the-loop or on-the-loop per action

Choose in-the-loop or on-the-loop per action

Comments 3
6 min read
Architecture choices that change memory, latency, and context

Architecture choices that change memory, latency, and context

Comments 1
5 min read
Re-reading Nov 2024 GenAI predictions as a builder playbook

Re-reading Nov 2024 GenAI predictions as a builder playbook

Comments
4 min read
Copy or federate? A per-source table for agent data access

Copy or federate? A per-source table for agent data access

Comments 2
5 min read
Screen an agent project for agent washing

Screen an agent project for agent washing

Comments
6 min read
Validate bounding boxes from a general vision model

Validate bounding boxes from a general vision model

Comments
6 min read
Five concepts to learn before you build with LLMs

Five concepts to learn before you build with LLMs

Comments
6 min read
Write your agent as functions first, add a framework later

Write your agent as functions first, add a framework later

Comments
5 min read
Pick the LLM eval metric before you build the dashboard

Pick the LLM eval metric before you build the dashboard

Comments
4 min read
Check each agent action after you grant the tool

Check each agent action after you grant the tool

Comments
5 min read
When to pay for a reasoning model on a request

When to pay for a reasoning model on a request

Comments 3
5 min read
Draft the file your agent loads at every session start

Draft the file your agent loads at every session start

Comments
5 min read
Design discovery, identity, and messages before adding agents

Design discovery, identity, and messages before adding agents

Comments
6 min read
Run GPU kernel tuning as an overnight search loop

Run GPU kernel tuning as an overnight search loop

Comments 1
6 min read
Ship the dependency fix before the exploit window closes

Ship the dependency fix before the exploit window closes

Comments 1
7 min read
Log what your tools put in the context window before blaming the model

Log what your tools put in the context window before blaming the model

Comments
4 min read
Test document extraction before an agent acts on it

Test document extraction before an agent acts on it

Comments
4 min read
Open weights in production: five builder takeaways from Chain of Thought

Open weights in production: five builder takeaways from Chain of Thought

Comments 2
5 min read
When your LLM plan moves a robot, clamp every command first

When your LLM plan moves a robot, clamp every command first

Comments
5 min read
Five agent episodes, and the build decision to take from each

Five agent episodes, and the build decision to take from each

Comments
4 min read
How to write tool descriptions agents won't misread

How to write tool descriptions agents won't misread

2
Comments 5
7 min read
Shipping practices from five AI engineering episodes

Shipping practices from five AI engineering episodes

Comments
5 min read
Checks to run before a small model serves traffic

Checks to run before a small model serves traffic

Comments 2
6 min read
Five podcast lessons on AI defensibility and go-to-market

Five podcast lessons on AI defensibility and go-to-market

Comments
4 min read
Tools before training for a domain legal agent

Tools before training for a domain legal agent

Comments
5 min read
Threat-model the model endpoint your app exposes to the internet

Threat-model the model endpoint your app exposes to the internet

Comments
5 min read
How to audit every credential your AI agent process can reach

How to audit every credential your AI agent process can reach

Comments
5 min read
Shrink a high-volume agent step after the strong model

Shrink a high-volume agent step after the strong model

Comments
6 min read
Scope chat agents with citations and multi-pass search

Scope chat agents with citations and multi-pass search

Comments 3
5 min read
Keep signing keys out of your AI agent's reach

Keep signing keys out of your AI agent's reach

Comments
5 min read
Labs: The Evolution of Continuous Merge

Labs: The Evolution of Continuous Merge

11
Comments
2 min read
6 Proven Strategies For Being A Great Platform Engineer

6 Proven Strategies For Being A Great Platform Engineer

13
Comments
5 min read
AI Tooling For Your Dev Team: To Adopt or Not to Adopt?

AI Tooling For Your Dev Team: To Adopt or Not to Adopt?

11
Comments
2 min read
Have Engineering Leaders Become Too Hands-off?

Have Engineering Leaders Become Too Hands-off?

16
Comments
2 min read
Reimagining DORA Metrics & Leveraging Feature Flags with Split

Reimagining DORA Metrics & Leveraging Feature Flags with Split

10
Comments
2 min read
The Art of Landing a DevRel Role with daily.dev

The Art of Landing a DevRel Role with daily.dev

11
Comments
2 min read
LB Labs: Inside the Top 10% of Engineering Orgs

LB Labs: Inside the Top 10% of Engineering Orgs

5
Comments
2 min read
loading...