Angie Jones ✓

@techgirl1908 · New Orleans, LA · joined 19 Dec 2014

VP, Agentic AI Foundation. Helping developers build with agents. I ❤️ open source

114 622Followers

729Following

83 125Posts total

61.6KViews on collected posts

Últimas publicaciones

Angie Jones ✓@techgirl19083 Sep

Hopping on a plane to kick off a world tour! I'm so excited for the very first editions of AGNTCon + MCPCon!!! First stop is Shanghai. Then we'll be in Tokyo next week. Then Amsterdam the week after! Really looking forward to seeing you all and discussing all things Agentic AI 3.3K views · 94 likes · 9 reposts · 9 replies Open on X →

Angie Jones ✓@techgirl19082 Sep

.@AgenticAIFdn now has a Sandbox phase!!! 🎉 Agentic AI is moving so fast that we don’t yet know which of today’s younger projects the industry will depend on tomorrow. Many exciting, innovative projects have working code and strong momentum, but they haven't had time to reach 2.9K views · 36 likes · 7 reposts · 1 replies Open on X →

Angie Jones ✓@techgirl19081 Sep

@techgirl1908 yep 100% - skills exist to get the model to do behaviors that are not the default in the weights. There are other ways to do this, eg pasting a prompt in, or writing a script that wraps an agent sdk that sets the first user message for a part of a pipeline (function 1.1K views · 11 likes · 0 reposts · 0 replies Open on X →

Angie Jones ✓@techgirl19081 Sep

My session is live! Quick 15 min talk on preparing engineering systems so agents can work beyond the codebase https://t.co/QbtwSgGulD 5.6K views · 32 likes · 13 reposts · 3 replies Open on X →

Angie Jones ✓@techgirl19081 Sep

@techgirl1908 Ridiculous. "Don't use markdown files with instructions ... let your agent use markdown files with instructions." 262 views · 8 likes · 0 reposts · 0 replies Open on X →

Angie Jones ✓@techgirl19081 Sep

@techgirl1908 Hi Angie! Skills are not the only way to give the model knowledge of a repeatable workflow; but to deliver workflows via skills constrains teams from properly utilizing the agents to their fullest extent. I tell the model how to work, not what to do. https://t.co/Zn 3.5K views · 13 likes · 0 reposts · 7 replies Open on X →

Angie Jones ✓@techgirl19081 Sep

ok I'm getting annoyed by the anti-skill rhetoric. skills are for REPEATABLE workflows that the model would not inherently know how to do consistently. why on earth would i want to burn time and tokens having agents figure the same thing out over and over when I could simply 22.3K views · 285 likes · 14 reposts · 41 replies Open on X →

Angie Jones ✓@techgirl19081 Sep

Here's how WebMCP differs from an MCP server for a website: - MCP tools work even when the website isn't open - WebMCP works on the page you currently have open. They use the page's current state and in your signed in session. Very helpful when you and your agent are 9.1K views · 95 likes · 7 reposts · 19 replies Open on X →

Angie Jones ✓@techgirl190831 Aug

@DanielMiessler Thank you! To expand a bit more on skills specifically: These machines are fundamentally trained to follow instructions. Skills are a way to supply instructions, and they’re privileged in the post-training sense: files on disk wired in as skills get very high 13.6K views · 52 likes · 3 reposts · 5 replies Open on X →

Frente a cuentas del mismo tamaño

9 publicaciones de los últimos 90 días, junto al rango de 100K–1M seguidores. llega mucho más allá de su propia audiencia, y esa audiencia responde.

Visualizaciones medianas3 529esta cuenta5 983mediana de 100K–1M

Alcance, %3.08%esta cuenta1.49%mediana de 100K–1M

Interacción, %1.39%esta cuenta0.93%mediana de 100K–1M

Métrica	Esta cuenta	Mediana de 100K–1M	Proporción
Visualizaciones medianas por publicación	3 529	5 983	0.59×
Alcance (visualizaciones ÷ seguidores)	3.08%	1.49%	2.07×
Tasa de interacción	1.39%	0.93%	1.49×

Otras cuentas de este rango → Comparar con otra cuenta → Cómo se construyen estas referencias →

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

13.6K31 Aug

9.1K1 Sep

22.3K

3.5K

262

5.6K

1.1K

2.9K2 Sep

3.3K3 Sep

Last 9 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.45%31 Aug

1.39%1 Sep

1.54%

0.57%

3.05%

0.87%

1.02%

1.54%2 Sep

3.41%3 Sep

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

What the audience does

Likes68.7%626 in total

Reposts5.8%53 in total

Replies9.3%85 in total

Quotes1.1%10 in total

Bookmarks15.0%137 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.

Últimas publicaciones

Frente a cuentas del mismo tamaño

Growth & engagement

Views per post

Engagement rate per post

What the audience does

Cuentas similares