ILIAS ISM profile photo

ILIAS ISM @illyism on X (Twitter): stats, voice and strategy

ILIAS ISM (@illyism) is an X (Twitter) creator with 31.5K followers who posts most about AI Agent Workflows. Across their last 200 posts they average a 0.94% engagement rate and 2.19 posts a day, busiest on Wednesdays.

Hook formulas, weaknesses and how to get their attention. Included in the free trial, then from $29 a month. See pricing

Followers
31.5K
Following
1.6K
Posts on X
17.6K
Engagement rate
0.94%
Posts a day
2.19
Reply share
1%

Counts as of ; averages from @illyism's last 200 posts. Engagement rate is likes, reposts and replies divided by views, averaged per post. View @illyism on X

@illyism is The Analyst

Brings receipts. Every take arrives with data attached.

  • Evidence over vibes
  • Long-form depth
  • Contrarian when earned

One of six archetypes Xpert reads from the published numbers: topics, cadence, reply habits and format mix. It is a heuristic label, not one ILIAS ISM chose.

How @illyism's posts perform

An average @illyism post gets 132 likes, 20 replies and 5 reposts from 33.7K views.

Per post, on average

Likes
132
Reposts
5
Replies
20
Views
33.7K
Median length
177 chars
Posts analyzed
200

Format mix

With media
59%
With links
56%
Ask a question
11%
Part of a thread
0%

Share of @illyism's last 200 posts. Replies make up 1% of their output.

When does @illyism post?

@illyism posts about 2.2 times a day, most often on Wednesdays and between 15:00 and 18:00 UTC. Engagement is heating up: 0.84% across the older half of recent posts, 1.04% across the newer half.

Posts by day of week
Sun: 5 posts, Mon: 24 posts, Tue: 36 posts, Wed: 54 posts, Thu: 43 posts, Fri: 18 posts, Sat: 20 posts
Posts by hour (UTC)
00-03: 13 posts, 03-06: 19 posts, 06-09: 37 posts, 09-12: 32 posts, 12-15: 21 posts, 15-18: 47 posts, 18-21: 17 posts, 21-24: 14 posts
Engagement trend

Heating up

0.84% to 1.04% (+0.2 pts, up)

Oldest half of recent posts against the newest half.

The busiest day and window are in amber. Hours are UTC.

What does @illyism post about?

Most often AI Agent Workflows (45% of recent posts), then SEO & Growth Hacking (25%), SaaS Decoupling & Self-hosting (20%) and Digital Nomad Lifestyle (10%).

AI summary of their voice

Sharp, cynical, and highly technical, Ilias writes from a place of 'radical utility'—he values speed and cost-efficiency above all else. He presents himself as a builder who has cut through the noise…

What they post about

AI Agent Workflows
45%
SEO & Growth Hacking
25%
SaaS Decoupling & Self-hosting
20%
Digital Nomad Lifestyle
10%

Words they lean on

  • seo×57 uses
  • link×54 uses
  • every×51 uses
  • agent×48 uses
  • google×43 uses

What works for @illyism

The 'Bloat vs. Lean' breakdown

He contrasts expensive, legacy SaaS stacks with his own zero-dependency, self-hosted alternatives, proving that complex problems often require simple, code-forward solutions.

One of 4 patterns. The rest are in the full analysis.

From one of their posts
Most of the tools I use daily now get operated by an agent through MCP rather than by me through a browser

@illyism's top recent posts

The most-liked of their last 200 posts, with the numbers X reported. Each opens the original.

ILIAS ISM

@illyism ·

The real alpha is buried at 31:50 when he talks about how Railway actually does marketing They went from $20M to ~$100M ARR this year with only 1 growth marketer and 1 product marketer Here is their actual GTM playbook from the interview: 1. "Incepting the AI models to recommend us more and more" (31:50) When a developer asks Claude Code, Cursor, or ChatGPT "where should I deploy my Postgres DB / backend?" the LLM picks the winner before the user ever opens Google 2. Zero-signup agent access (09:20) They shipped an MCP, a CLI agent, and `ssh railway new` so an AI agent can spin up a VM immediately without even creating an account 3. Reverse-engineering what already works in marketing (13:47) Despite the quote about ignoring Stripe and Cursor on engineering, 3 minutes later he admits they have a #marketintel channel where they reverse-engineer Ramp's marketing and improve on it 4. GTM writes code instead of hiring headcount (25:35) Their 7-person GTM team builds automated systems instead of doing manual outreach This is the exact shift I've been talking about all year: AI agents are the buyers now, and the way you "incept" Claude, ChatGPT, and Perplexity to recommend your product is by dominating the third-party listicles, docs, and comparison pages those models cite If you want to run this exact playbook without hiring a marketing team: 1. Check which competitors ChatGPT & Claude recommend for your prompts (and which URLs they cite) → https://t.co/UT6ptWDCWN 2. Get placed into those exact ranking listicles & high-DR sites automatically → https://t.co/fiqqEJPROE (or just tell Claude Code to read https://t.co/cVTq61u3wH)

16 replies39 reposts758 likes60.5K views

What the full analysis adds

The full analysis of @illyism goes past the public numbers: the hooks they rely on, the patterns that work, the weaknesses holding the account back, and how to get their attention.

The rest of @illyism's analysis

  • 6 opening-hook formulas, as reusable templates
  • 3 more what-works patterns with real quotes
  • 3 weaknesses holding the account back
  • How to get their attention: what to reply to, in what tone
  • 6 more top posts plus cadence detail
Unlock the full analysis

Included in the free trial, then from $29 a month. Card required, cancel anytime.

The blurred text is a placeholder, not @illyism's analysis. The real one stays on our server until you unlock it.