tweetindex
EN
EnglishEspañolItalianoDeutschBahasa IndonesiaPortuguêsРусскийFrançaisไทยTürkçe

MLflow ✓

@MLflow · San Francisco, CA · joined 04 Aug 2018

The open source developer platform to build AI applications and models with confidence.

11 726Followers
48Following
1 321Posts total
2.7KViews on collected posts

Latest posts

MLflow ✓@MLflow
A multi-agent app can return 200 OK and still be wrong. Request dashboards miss bad tool calls, empty MCP data, and stale-prompt token burn. In this video, @LegareKerrison (@RedHat) covers MLflow tracing, LLM-as-judge evals, and production setup. 🎥 Watch: 218 views · 2 likes · 0 reposts · 1 replies Open on X →
MLflow ✓@MLflow
@MLflow The split between an async FastMCP client and scoped genai/traditional ML tools is a useful design choice. Keeping the 20–30 read/write operations local or next to tracking should make governance and latency much easier to reason about. 3 views · 0 likes · 0 reposts · 0 replies Open on X →
MLflow ✓@MLflow
@MLflow Love this take 13 views · 0 likes · 0 reposts · 0 replies Open on X →
MLflow ✓@MLflow
@MLflow This is a compelling bridge from natural-language assistance to traceable operations. Local or adjacent deployment plus explicit read/write scope should make MCP adoption easier to review and govern. 7 views · 0 likes · 0 reposts · 0 replies Open on X →
MLflow ✓@MLflow
Use the MLflow MCP server to query tracking data from code or an assistant. 👇 🔹 Async Python FastMCP client, scoped to genai or traditional ml tools 🔹 Configure Claude, VS Code, or Cursor, then ask in plain English 🔹 ~20–30 read/write tools; runs locally or next to tracking 853 views · 10 likes · 1 reposts · 5 replies Open on X →
MLflow ✓@MLflow
@MLflow The session grouping and custom columns are especially practical; treating trace metadata as a first-class navigation tool should shorten the path from anomaly to root cause. 5 views · 0 likes · 0 reposts · 0 replies Open on X →
MLflow ✓@MLflow
@MLflow Making the rebuilt trace explorer the default is a strong usability win: dense tables help triage, while span trees preserve causal detail. Folding multi-turn sessions into the same view should also make agent debugging much less fragmented. 6 views · 0 likes · 0 reposts · 0 replies Open on X →
MLflow ✓@MLflow
@MLflow The focus on trace density, drill-down, metadata columns, and multi-turn grouping makes this feel like a real observability workflow improvement—not just a visual refresh. The default experience should lower the friction of debugging agent runs. 2 views · 0 likes · 0 reposts · 0 replies Open on X →
MLflow ✓@MLflow
The trace explorer in MLflow 3.16.0 has been rebuilt from the ground up and is now the default traces experience. 🔹 Traces table: Tighter row density, a cleaner header, and smoother navigation 🔹 Span-tree explorer: Redesigned for faster drill-down 🔹 Custom columns: Reorder htt
0:33
636 views · 12 likes · 0 reposts · 3 replies Open on X →
MLflow ✓@MLflow
2 weeks until Open Lakehouse + AI Meetup in Paris 🇫🇷 Building with MLflow? Don't miss @omnigent_ai: A Meta Harness for AI Agents. Aravind Segu and Edwin He will show how to capture @opentelemetry traces for observability in MLflow across multi-harness agent workflows. 🗓️ Sept h
504 views · 9 likes · 1 reposts · 1 replies Open on X →
MLflow ✓@MLflow
What’s New in MLflow: September 2026 Roundup https://t.co/V9EJELV9XV 478 views · 6 likes · 1 reposts · 0 replies Open on X →

Against accounts of the same size

11 posts from the last 90 days, next to the 10K–100K follower range. reaches fewer people than peers of the same size.

Median views13this account924median for 10K–100K
Reach, %0.11%this account3.62%median for 10K–100K
Engagement, %0.00%this account1.52%median for 10K–100K
MetricThis accountMedian for 10K–100KRatio
Median views per post139240.01×
Reach (views ÷ followers)0.11%3.62%0.03×
Engagement rate0.00%1.52%0.00×

Others in this range →   Compare with another account →   How these benchmarks are built →

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

4789 Sep
50411 Sep
63614 Sep
215 Sep
616 Sep
517 Sep
85318 Sep
7
13
322 Sep
21823 Sep

Last 11 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

1.46%9 Sep
2.38%11 Sep
2.36%14 Sep
0.00%15 Sep
0.00%16 Sep
0.00%17 Sep
1.88%18 Sep
0.00%
0.00%
0.00%22 Sep
1.38%23 Sep

Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.52%.

What the audience does

Likes57.4%39 in total
Reposts4.4%3 in total
Replies14.7%10 in total
Quotes1.5%1 in total
Bookmarks22.1%15 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.

Similar accounts

Floki ✓ @CryptoFloki 23.5K followers · 90.7K posts Ceaser Wrestling ✓ @CeaserWrestles 23.5K followers · 15.7K posts Head In The Clouds Festival @hitcfestival 23.5K followers · 991 posts SNELLY (TONY SNELL) @snellyradio 23.5K followers · 11.8K posts Minal Sultan @Itz_Iyla 23.5K followers · 397.4K posts Michael Kovrig ✓ @MichaelKovrig 23.5K followers · 6.4K posts Andres ADF 🇬🇹 ✓ @andresNadf 23.5K followers · 51.5K posts M Y ∆ Z I S T O™ ✓ @MyazistoZA 23.4K followers · 12.8K posts