Harrison Chase ✓

@hwchase17 · joined 29 Jul 2014

@LangChain Always hiring: https://t.co/D5Ut3loFO7

128 787Followers

585Following

17 464Posts total

434KViews on collected posts

Son gönderiler

Harrison Chase ✓@hwchase173 Sep

This is very true, and something we still try to do for all products (and even features) we launch. Find a small group of customers who we think will push us the most on product and then build for them and make them happy 5.4K views · 26 likes · 4 reposts · 2 replies Open on X →

Harrison Chase ✓@hwchase173 Sep

Agent workspaces should be durable, inspectable, and swappable Deep Agents’ virtual file system is intentionally behind a BackendProtocol, so the agent code can keep using read/write/glob/grep while teams choose the storage layer that fits production Nice to see MongoDB support 5.2K views · 42 likes · 4 reposts · 16 replies Open on X →

Harrison Chase ✓@hwchase172 Sep

we have an absolutely killer lineup for our Interrupt conference in NYC (sept 24th) in particular, im excited about the fireside chats we're doing with with founders at different parts of the agent stack: - @alexatallah: openrouter is a key part of how companies maintain model 8K views · 56 likes · 11 reposts · 11 replies Open on X →

Harrison Chase ✓@hwchase172 Sep

@hwchase17 good, most debugging tools assume you already speak fluent trace, this assumes you speak english 87 views · 1 likes · 0 reposts · 0 replies Open on X →

Harrison Chase ✓@hwchase172 Sep

@hwchase17 following a trace like a chat is a UX win, whether the chat was worth having is still an unanswered question 49 views · 1 likes · 0 reposts · 0 replies Open on X →

Harrison Chase ✓@hwchase172 Sep

@hwchase17 chat view is great until a tool call result is 20kb of json, then you're back to squinting at a bubble 58 views · 1 likes · 0 reposts · 0 replies Open on X →

Harrison Chase ✓@hwchase172 Sep

Agent traces shouldn’t only be useful to infra teams For most builders, the fastest way to debug an agent is to replay the conversation + tool calls in the shape the agent experienced them That’s the idea behind Messages View in LangSmith 11.5K views · 80 likes · 12 reposts · 37 replies Open on X →

Harrison Chase ✓@hwchase171 Sep

The new LangSmith “Messages View” dropped into my account (beta rollout) Makes following @LangChain traces as easy as following the chat! https://t.co/8t1Ds8fibc 10.4K views · 12 likes · 2 reposts · 2 replies Open on X →

Harrison Chase ✓@hwchase171 Sep

More on how early customers shape your business (@cursor_ai early work with Shopify, OpenAI, NVIDIA): "Not all ARR early on is created equal. It's not about just that number. It's about the genetics. I care far more that you've selected and are working with really thoughtful, h 6.9K views · 8 likes · 3 reposts · 1 replies Open on X →

Harrison Chase ✓@hwchase171 Sep

Deep research is a complex, multi-step search and synthesis workflow This is exactly the kind of workflow Deep Agents is meant to make easier to build 7.5K views · 32 likes · 2 reposts · 12 replies Open on X →

Harrison Chase ✓@hwchase171 Sep

❤️ still early, lots to build, keep the feedback coming 7.7K views · 38 likes · 0 reposts · 6 replies Open on X →

Harrison Chase ✓@hwchase171 Sep

I have been using langgraph for like a year and a half now and i can easily say the growth this company has had and the way they have listened to the community is quite remarkably unmatched. Awesome work @hwchase17 7.4K views · 9 likes · 0 reposts · 0 replies Open on X →

Harrison Chase ✓@hwchase179 Aug

@hwchase17 Simple way to Manage Deep Agents!!! https://t.co/4yjWvWFAmn 2.4K views · 7 likes · 1 reposts · 0 replies Open on X →

Harrison Chase ✓@hwchase177 Aug

@hwchase17 The shift from building agents to managing production agents is huge 4.4K views · 4 likes · 2 reposts · 0 replies Open on X →

Harrison Chase ✓@hwchase177 Aug

@hwchase17 auth is the one on that list I'd hesitate to bundle. once the agent is acting as someone against external systems, that's your permission model, not the harness's. 151 views · 2 likes · 0 reposts · 0 replies Open on X →

Harrison Chase ✓@hwchase177 Aug

https://t.co/NnFGj7FSYK 356.9K views · 883 likes · 107 reposts · 52 replies Open on X →

Aynı büyüklükteki hesaplara karşı

Son 90 güne ait 16 gönderi, 100K–1M takipçi aralığıyla yan yana. geniş kitleye gösteriliyor, ama izleyenlerin azı tepki veriyor.

Medyan görüntülenme6 136bu hesap5 983100K–1M için medyan

Erişim, %4.76%bu hesap1.49%100K–1M için medyan

Etkileşim, %0.60%bu hesap0.93%100K–1M için medyan

Ölçüt	Bu hesap	100K–1M için medyan	Oran
Gönderi başına medyan görüntülenme	6 136	5 983	1.03×
Erişim (görüntülenme ÷ takipçi)	4.76%	1.49%	3.20×
Etkileşim oranı	0.60%	0.93%	0.65×

Bu aralıktaki diğer hesaplar → Başka bir hesapla karşılaştır → Bu kıyas değerleri nasıl kuruluyor →

Growth & engagement

How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.

Views per post

4.4K7 Aug

2.4K9 Aug

7.4K1 Sep

7.7K

7.5K

6.9K

10.4K

11.5K2 Sep

5.2K3 Sep

5.4K

Last 14 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.13%7 Aug

0.34%9 Aug

0.14%1 Sep

0.57%

0.61%

0.19%

0.16%

1.13%2 Sep

1.72%

2.04%

1.15%

1.01%

1.19%3 Sep

0.59%

Reactions — likes, reposts, replies and quotes — divided by views. Median for 100K–1M accounts is 0.93%.

What the audience does

Likes35.7%1 202 in total

Reposts4.4%148 in total

Replies4.1%139 in total

Quotes1.1%36 in total

Bookmarks54.8%1 846 in total

Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.

The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.

Son gönderiler

Aynı büyüklükteki hesaplara karşı

Growth & engagement

Views per post

Engagement rate per post

What the audience does

Benzer hesaplar