Darragh Kennedy (@darraghke) header
Darragh Kennedy (@darraghke) profile picture

Director of Engineering @Zendesk - views are my own

Melbourne
Joined April 2009
Photo by Darragh Kennedy (@darraghke)Photo by Darragh Kennedy (@darraghke)Photo by Darragh Kennedy (@darraghke)Photo by Darragh Kennedy (@darraghke)Photo by Darragh Kennedy (@darraghke)Photo by Darragh Kennedy (@darraghke)Photo by Darragh Kennedy (@darraghke)Photo by Darragh Kennedy (@darraghke)Photo by Darragh Kennedy (@darraghke)
Darragh Kennedy retweeted
"... we didn’t start by asking, 'how do we deploy faster?' We asked the better question, 'How do we remove the reasons we’ve always had to go slow?'" medium.com/mcdonalds-technic… < great story about McDonald's tech team dramatically improving pace of updates to restaurants
3
535
Darragh Kennedy retweeted
We're releasing new @Stripe agentic commerce data today, telling the story so far as we look ahead to the kickoff of the holiday season next week.
47
58
42
320
60,594
Darragh Kennedy retweeted
On this slow news day, we just launched Stripe evals to measure how well coding agents build real Stripe integrations. A few cool (to me) learnings: • Our plugin helped every harness/model pair we tested. All 14 configurations scored ~3–8 percentage points higher with Stripe’s recommended skills and tools. • Agents searched less and wrote fewer tests with the plugin. Web searches dropped 96% and (often extraneous) test code dropped ~40%, while scores improved. • We used another agent to role-play the developer. The role-player starts by sharing its imperfectly-stated goals, asks follow-up questions, and works through a few rounds of conversation with its coding agent. • The last mile is hard. Agents satisfied ~78% of criteria on average, but only ~29% of runs met every required criterion. Results and methodology: stripe.dev/evals
41
13
8
106
13,581
Darragh Kennedy retweeted
Introducing Tool Retrieval in the Gemini API ✨ With Tool Retrieval, you can scale to hundreds of tools without context bloat. Load parameter schemas on demand to preserve selection accuracy, cut tokens, and keep your prefix cache intact. Read the blog: goo.gle/4ALQwgM
45
95
34
983
117,462
Darragh Kennedy retweeted
We spent two days trying to hack ourselves with abliterated models. The biggest risks we found, by far, were side channels into our infra, outside the application code. Stuff like: - The oneoff dev env we set up to test out Coder that had way too much access - CI runners had tailnet access for no good reason We’ve scanned our application code many times over, but there were a lot of scary risks hiding in these side doors and third party vectors. All problems that were very easy to mitigate once we were aware of them. Many of the high-profile hacks from the past two weeks happened this way. Application code held up fine, but the company had a massive breach due to a vulnerability in a vibecoded internal tool or an unpinned CI dependency or third party js or … You’ll see us incorporating this pov into our vuln scans. (And of course we’ll continue perpetually trying to hack ourselves!)
20
18
1
330
26,969
Darragh Kennedy retweeted
The first 100,000 CVEs took 18 and a half years to publish (Sep 1999 to Apr 2018). 2026 published 100,000 in 322 days.
35
236
55
1,119
109,450
Bending Spoons just bought Mailchimp for $3.68 billion. Intuit paid $12 billion for it in 2021. Mailchimp actually got the best price of the five big names Bending Spoons has bought, measured against each one’s peak valuation: - Miro: $17.5B peak (Jan 2022). Sold for about $1.79B. 10 cents on the dollar. - Vimeo: $7.2B at its 2021 spin-off. Sold for $1.38B. 19 cents. - Airtable: $11B peak (Dec 2021). Sold for about $2.25B. 20 cents. - Eventbrite: $1.76B at its 2018 IPO. Sold for $500M. 28 cents. - Mailchimp: $12B in 2021. Sold for $3.68B. 31 cents. None of these companies were DOA. They’re big, well-known, mostly recurring businesses with millions of customers. They stopped growing, and in 2026 a big B2B company that isn’t growing sells for 2-3x revenue. Mailchimp is guiding to 0% growth this year on about $1.26B of revenue. In 2021 it was growing 20% on $800M, which is how it got 15x. If you run a B2B company growing under 10%, these five deals are your comps now, not your last round. Bending Spoons will pay for cash flow it can squeeze, and a reorg comes with the check.
52
23
13
222
31,037
Darragh Kennedy retweeted
Anthropic vs OpenAI.
10
33
9
329
36,525
Darragh Kennedy retweeted
Building the Agent Host Protocol for sessions that continue across devices github.blog/engineering/engi… < from the @github team, looking for ways to get past one integration per client
3
1
24
1,310
Darragh Kennedy retweeted
We got a LOT of questions about how the new Copilot Fusion works under the hood. @aashna and friends walk us through the science and engineering details that lead to this breakthrough: youtu.be/1kpeIbdAfoQ?si=p6Wq…
"Just today, GitHub Copilot Fusion was ranked as the #1 coding agent on Terminal Bench scoring 5 points over Claude Code at less than half the cost." tbench.ai
5
23
1
113
13,062
Darragh Kennedy retweeted
Everyone's using AI to write code. But a huge additional unlock, which less people are doing, is combining the code with the context of all your live infra. Database performance. Logs. Etc. Agents can do so much better when your code and production context are combined. The world needs more p99 cliff diagrams, here's how you get there: planetscale.com/blog/buildin…
25
11
327
10,199
Darragh Kennedy retweeted
QConSF highlights the general state of confusion in the industry. Half the speakers advocate to give agents work in smallish chunks, to avoid them latching into a minor requirement and creating a lot of complexity early just for this minor bit (that could be easily added later). Fleshing out features iteratively. Half the speakers recommend fleshing out a complete spec with all the edge cases and complexities, and giving this long deep spec to the agent to build, test and ship.
17
6
2
47
5,817
Darragh Kennedy retweeted
New blog post, with an ice-cold take on some of the last week's systems news: brooker.co.za/blog/2026/11/1… The throughput of real-world systems can vary (a lot!) based on subtle properties of the workload they're handling. Load tests that don't match the workload are useless.
5
14
99
6,018
Darragh Kennedy retweeted
in case you missed it: muse launched in australia yesterday!! 🇦🇺 🦘 the early reception has been awesome, give it a shot!
140
65
31
1,387
85,818
Darragh Kennedy retweeted
GitHub Copilot Evals is now in public preview to help optimize Copilot for your skills, agents, and tools. • Create repeatable AI behavior tests to check results and catch regressions github.blog/changelog/2026-1…
6
18
3
190
11,812
Darragh Kennedy retweeted
Close. Those. Deals…with the new ChatGPT for Sales experience. It brings together our new Sales plugin and 30+ new and enhanced partner plugins to put your sales tools and customer context to work—so your team can spend less time on busywork and keep deals moving. openai.com/index/introducing…
133
256
187
4,088
806,662
Darragh Kennedy retweeted
Five Bots now have full-time roles on our accounting team. We onboard, train, and manage them just like human teammates. Here's how we built them to handle the order-to-cash process, from provisioning customer accounts to collecting payments. x.ai/news/grok-bot-accountin…
1,495
814
221
11,162
3,774,574
Darragh Kennedy retweeted
“Everything fails, all the time." So we stopped waiting for failover. Multipath Resilience is now GA: identical packets across physically diverse AWS backbone paths at once. First one in wins. One flag to turn on. 99.999% SLA. Live today with @stripe and @boostmobile. go.aws/4kmJwlo
6
16
8
193
32,795