Ercan Er

874 posts

Ercan Er banner
Ercan Er

Ercan Er

@Dev_ErcanEr

Co-founder @ironbee_ai | Ex-@Catchpoint, Ex-@thundra (both acquired)

Ankara, Türkiye Katılım Ocak 2010
1.1K Takip Edilen736 Takipçiler
Ercan Er
Ercan Er@Dev_ErcanEr·
The first part of the IronBee product video series is live. With IronBee, we are building an autonomous verification and intelligence layer for AI-generated code. Fully replayable runs, timelines, traces, diffs, browser sessions, and proof-backed verifications. Built with @Remotion , which made creating this product video much smoother. We would love feedback from teams using AI agents. Waitlist: ironbee.ai #IronBee #Remotion #AIAgents #CodingAgents #AICoding #AIEngineering #DevTools #DeveloperTools #SoftwareTesting #CodeVerification #AgenticAI #TestAutomation
Serkan Özal@serkan_ozal

Here is first part of the @ironbee_ai product video series (Thanks @Dev_ErcanEr for the video). AI writes more code than ever. But verifying AI-generated code is still manual, fragmented, and slow. We are building IronBee. An autonomous verification and intelligence layer for AI coding agents. IronBee tests, verifies, analyzes, debugs, and fixes AI-generated code while recording every step end to end. Every tool call. Every browser interaction. Every verification flow. Fully replayable. Here is what you can do with IronBee: - See it. Every run on one timeline. - Spot it. Verdict at a glance when something breaks. - Fix it. The diff right next to the failed span. - Replay it. Click any tool call, the browser jumps to that moment. - Watch it. Scrub through the recorded session like a movie. - Track it. Every step and every screenshot captured. - Prove it. Verifications with proof. Early access is opening very soon. If this resonates with you, hop on the waitlist at ironbee.ai Would love feedback from anyone shipping with agents in production.

English
0
1
1
179
Ercan Er
Ercan Er@Dev_ErcanEr·
@altugx @elonmusk Qatar Airways ile mi uçtunuz? Starlink Aviation’ın THY de olmadığını biliyorum, o yüzden merak ettim.
Türkçe
1
0
0
141
Altuğ Öztürk
Altuğ Öztürk@altugx·
Uçakta starlink çok keyifliymiş. Eyvallah @elonmusk reis. Sayende uçarken evimde gibi internet kullanabiliyorum. Bir ton iş bitirdim. 😌
Türkçe
2
0
25
7.4K
Ercan Er
Ercan Er@Dev_ErcanEr·
Building this as @ironbee_ai is incredibly exciting. The future of AI agents isn’t just code generation; it’s understanding real environments, interacting with live products, and solving problems end to end. This is only the beginning
Serkan Özal@serkan_ozal

@ironbee_ai's Browser DevTools MCP is now used by developers in 130+ countries. It gives AI agents direct access to the browser: seeing the UI, understanding flows, and debugging issues in real time. If we want AI to move beyond code generation, we need to give it real execution visibility. That’s the layer we’re building ... ironbee.ai/products/brows…

English
0
0
2
85
Ercan Er retweetledi
Serkan Özal
Serkan Özal@serkan_ozal·
@ironbee_ai's Browser DevTools MCP is now used by developers in 130+ countries. It gives AI agents direct access to the browser: seeing the UI, understanding flows, and debugging issues in real time. If we want AI to move beyond code generation, we need to give it real execution visibility. That’s the layer we’re building ... ironbee.ai/products/brows…
Serkan Özal tweet media
English
1
1
5
417
Ercan Er retweetledi
Serkan Özal
Serkan Özal@serkan_ozal·
While building @ironbee_ai's telemetry pipeline for @claudeai Code, to deliver deeper analytics and smarter recommendations for agentic coding sessions, I hit two gaps in the hook and @opentelemetry surfaces that were blocking key insights: - No "duration_ms" in "PostToolUse" / "PostToolUseFailure" hooks, making it impossible to answer basic questions like "which tool calls took longer than 5 seconds?" without fragile workarounds. - No "tool_use_id" or "tool_input_size_bytes" in the "claude_code.tool_result" OTel event, blocking clean correlation between hook events and OTel logs, and forcing a privacy trade-off just to learn input sizes. I opened two feature requests on the Claude Code repo detailing the use cases and proposed solutions, and the @AnthropicAI team shipped both within days. 🙌 Huge thanks to the Claude Code team for being this responsive to ecosystem feedback. These small schema additions unlock fleet-wide dashboards, p95/p99 tool latency tracking, and clean joins between hook and OTel data: exactly what IronBee users need to understand and optimize their AI coding workflows. If you're building observability on top of Claude Code, it just got a lot easier. - github.com/anthropics/cla… - github.com/anthropics/cla…
English
1
1
5
204
Ercan Er retweetledi
Serkan Özal
Serkan Özal@serkan_ozal·
Big congrats to the Bindplane team on joining Dynatrace! 👏 As someone building in this space, I find this acquisition deeply validating. The thesis is clear: as AI becomes central to how we build and operate software, the quality and control of operational data becomes everything. Bindplane understood this early by giving teams a control plane for telemetry before it hits the platform. That's a powerful idea, and Dynatrace clearly agrees. We're building @ironbee_ai with a complementary but different bet: What if the AI agent itself could decide what data it needs and go get it? Today's observability is built on a "collect everything, query later" model. But when AI agents are writing code, deploying it, and then need to debug production issues, that model breaks. You either don't have the right data, or you're drowning in irrelevant signals. IronBee flips this. Our browser agent and runtime instrumentation let AI coding agents dynamically observe their own impact on production by pulling exactly the app state, logs, traces, and environment data needed for root cause analysis, on demand. forbes.com/sites/stevemcd…
English
1
1
3
365
Ercan Er retweetledi
Bora Özkent⎪ABD Borsası & Teknoloji Yatırımları
Bora Özkent⎪ABD Borsası & Teknoloji Yatırımları@BoraOzkent·
Dubai ülke ETF'i savaş öncesi zirvesine henüz dönmesiyse de kayıplarını epeyce telafi etti. Daha da ilginci son bir yılda %18 pozitif getiri sağladı. Dubai bitti diyen değerli analistlerimizi dinlemek yerine dipten alım yapsaydınız sadece bir ayda %11 kardaydınız. Biz küçük bir swingle biraz nemalandık. Diyeceğim o ki dünyayı anlamak istiyorsanız parayı takip edin, işkembeci, tribünlere oynayan ve dibine kadar ideolojiye gömülmüş analistleri değil. Çünkü para gerçeklere odaklanır, laf salatalarına değil.
Bora Özkent⎪ABD Borsası & Teknoloji Yatırımları tweet media
Türkçe
12
8
254
55.3K
Ercan Er
Ercan Er@Dev_ErcanEr·
This makes a lot of sense. Lambda + agents feels like a very natural fit when state is externalized. Curious to see more real-world examples
Serkan Özal@serkan_ozal

I’ve been designing an execution environment for agents on @awscloud using the @claudeai Agent SDK as part of what we’re building at @ironbee_ai. I’m currently evaluating AWS Lambda as the core runtime. There are still some tricks needed to make Lambda a good fit for agent execution. But being an AWS Serverless Hero and having run many different production workloads on Lambda over the years, it wasn’t too hard to adapt. What makes it interesting (especially with some of the recent AWS updates over the last year): - Natural scalability out of the box - Ephemeral runtime (fits prompt-scoped runs well) - Native per-invocation isolation, now reinforced with tenant isolation features that provide stronger guarantees for running multi-tenant or untrusted workloads - Amazon S3 Files for both context injection and session continuity / artifact storage - Can be extended into durable executions where agent workflows are checkpointed, paused, and resumed across invocations with built-in retries and state management Using S3 Files as a backing layer for sessions also changes the equation as the 15 minute execution limit becomes much less of a constraint when state and artifacts are externalized. One thing that surprised me: I haven’t really seen such examples of agents executed this way on Lambda. Feels like a pretty natural fit. #Serverless #AWS #AIAgents

English
0
0
1
51
Ercan Er retweetledi
Serkan Özal
Serkan Özal@serkan_ozal·
Browser DevTools MCP has crossed 100K+ installs on NPM, 10K+ installs on the Cursor marketplace, and now has 500+ daily active users. This growth shows a clear shift. Developers want AI that understands runtime, not just code. Most issues appear during execution, in the DOM, network, and async flows. Browser DevTools MCP brings that runtime visibility into AI workflows, helping agents observe real behavior instead of guessing. It is developed by the @ironbee_ai team and is also a core part of IronBee, a verification and intelligence layer for agentic development. Verification and debugging should be based on real execution, not assumptions. Thanks to everyone building with it. NPM: npmjs.com/package/browse… Cursor Extension: open-vsx.org/extension/serk… Web Site: ironbee.ai/products/brows…
Serkan Özal tweet media
English
1
2
3
241
Ercan Er
Ercan Er@Dev_ErcanEr·
I turned Browser DevTools MCP tool activity into a tiny pixel world in @cursor_ai Pixel characters react to what the tools are doing and make the in between moments way more fun (Thanks to @PixelLabAI ). Started as a small side project and opened it up for contributions. Repo in replies Made by @ironbee_ai team
Ercan Er tweet media
English
0
2
2
675
Ercan Er
Ercan Er@Dev_ErcanEr·
Bu dökümanda yazanlar doğru ise Anthropic’in Mythos modeliyle herşey değişecek gibi duruyor. Eskiden bir açığın keşfedilip exploit edilmesi aylar sürerdi, şimdi dakikalara iniyor. Üstelik: • 27 yıllık OpenBSD açığını buluyor • 16 yıllık FFmpeg bug’ını yakalıyor (milyonlarca testten kaçmış) • Linux kernel’da privilege escalation zinciri kuruyor Bu sadece hız değil, başka bir seviye…
Boris Cherny@bcherny

Mythos is very powerful, and should feel terrifying. I am proud of our approach to responsibly preview it with cyber defenders, rather than generally releasing it into the wild. Model card here: www-cdn.anthropic.com/53566bf5440a10…

Türkçe
0
1
2
346
Ercan Er
Ercan Er@Dev_ErcanEr·
#Anthropic’in başlattığı Project Glasswing biraz ürkütücü ama bir o kadar da kritik ve önemli Yapay zeka artık yazılım açıklarını çoğu insandan daha iyi bulabiliyor. Bu gücü ya saldırı olacak kullanacaklar ya da savunma. Yazdıklarına göre onlar savunmayı seçmiş. Ama gerçek şu: Güvenlik şirketleri başta olmak üzere artık oyunun kuralları değişiyor.
Anthropic@AnthropicAI

Introducing Project Glasswing: an urgent initiative to help secure the world’s most critical software. It’s powered by our newest frontier model, Claude Mythos Preview, which can find software vulnerabilities better than all but the most skilled humans. anthropic.com/glasswing

Türkçe
1
1
2
252
Ercan Er retweetledi
Serkan Özal
Serkan Özal@serkan_ozal·
AI writes code in seconds, but verification still lags behind. That gap is the real bottleneck. With IronBee’s open-source GitHub Action (github.com/ironbee-ai/iro…), we’re starting to close it. Would love your feedback 👇
Süleyman Barman@suleyman_barman

ai can generate code in seconds but verifying and auditing it inside our CI CD pipelines does not happen at the same speed. to clear this bottleneck we just released a github action that we open sourced. another step for ironbee is now complete. would love hear your feedback both here and github page. repo link below. github.com/ironbee-ai/iro…

English
1
1
4
525
Ercan Er
Ercan Er@Dev_ErcanEr·
“Introducing IronBee: The Verification and Intelligence Layer for AI Coding Agents” by Serkan Özal @serkan_ozal/introducing-ironbee-the-verification-and-intelligence-layer-for-ai-coding-agents-dd554279efa3" target="_blank" rel="nofollow noopener">medium.com/@serkan_ozal/i…
Ercan Er tweet media
Dansk
0
0
0
33
Ercan Er retweetledi
Süleyman Barman
Süleyman Barman@suleyman_barman·
AI agents can code an app in hours, but what does it actually cost to automate the testing? I benchmarked 4 models (Sonnet, Haiku, Kimi, MiniMax) using real API bills. Surprise: The run with the fewest tokens was actually the most expensive! Full breakdown & receipts, @suleyman.barman/the-real-cost-of-running-llms-for-browser-test-automation-535afc9e0df9" target="_blank" rel="nofollow noopener">medium.com/@suleyman.barm… #AIAgents #LLMs #MCP
English
1
2
2
271
Ercan Er
Ercan Er@Dev_ErcanEr·
A very interesting comparison for AI browser agents. Browser DevTools MCP can dramatically reduce token usage which directly impacts cost while also showing strong performance in browser automation. Efficiency in tokens, cost, and speed makes this approach really compelling. #mcp #playwright #ai #agent
Serkan Özal@serkan_ozal

We benchmarked Browser DevTools MCP vs Playwright MCP on the same flow: → 78% fewer tokens → 76% fewer turns → 66% lower cost → 57% faster → Much more consistent run-to-run How we did it (tool design, execute batching, scoping): @serkan_ozal/browser-devtools-mcp-78-fewer-tokens-vs-playwright-mcp-faster-and-more-consistent-32f314004d30" target="_blank" rel="nofollow noopener">medium.com/@serkan_ozal/b…

English
3
1
1
369

Keşfet

@Remotion @altugx @elonmusk @ironbee_ai @claudeai @opentelemetry @AnthropicAI @cursor_ai