4 min read · Published · Updated
When to use which of LoL2LLM's five personas, plus the one-line additions that turn a generic answer into a sharp one.

CHAMPION LENS
Jhin
Elise
Azir
Braum
VayneLoL2LLM ships five built-in personas (Coach, Roast, Praise, Caster, Analyst) and copies the matching persona prompt along with your match JSON. Pasting and hitting enter works, but one or two extra lines of context after the JSON make it much easier to steer the answer toward what you actually want to know. Here's when to use each persona, and the four prompt additions that make all of them sharper.
Coach: the default. Balanced criticism with concrete improvement steps. Works on both wins and losses; if you're unsure, start here.
Roast: for games you already know you played badly. Brutal, no-mercy critique. Useful when you need a kick to drive change — not when you're tilted.
Praise: a mental-reset tool after a tilting loss streak. Defends you and credits team-gacha for the loss. You learn nothing — that's the point. You come back ready to focus next game.
Caster: e-sports shoutcaster style. Best for sharing a game with friends or a stream chat — the dramatized read becomes a fun copy-paste comment, not a coaching note.
Analyst: cold, numeric evaluation, centered on the gaps to your lane opponent in CS, damage efficiency, and gold.
Persona prompts are intentionally generic, so the AI returns generic feedback. One sharper line at the end of the paste:
I lost CS badly to my laner this game. Restrict the analysis to how I played the lane and tell me which decisions probably went wrong, as far as the data can support.
Without context, the AI defaults to evaluating against pro play. Saying "I'm a Gold III jungle main" reshapes the advice into things actually executable at that level.
I'm a Gold III jungle main. Skip pro-level macro suggestions; only give advice that's realistically executable at this rank.
Left alone, an LLM may list every issue it can find. You can't fix all of them next game, and now you have to do the prioritization work yourself. Asking for the top three forces the model to rank, and gives you a focused practice list.
Limit feedback to the three highest-impact issues. For each, give one sentence on why it mattered and one sentence on what to do differently next game.
Paste your last five exports in sequence and ask "what's the recurring pattern across these games?". Single-match analysis can't catch repeating habits. You'll often hear something specific you didn't notice yourself — "your CS finished below your lane opponent's in 4 of 5 games" type observations.
Both are competent; their strengths differ. In my use, ChatGPT tended to produce cleaner bulleted action plans. Claude was better at long-form, narrative reads of complex teamfights and macro mistakes — it would explain why a rotation was wrong rather than just naming it. For Roast, ChatGPT bit harder; for dense teamfight breakdowns, Claude read more like a coach. Both change as their models are updated, though, so the reliable move is to paste the same JSON into the current model of each and compare.
Current meta and patch-specific tier lists are unreliable from an LLM — the knowledge cutoff is months old and bans/buffs move fast. For "is this champ strong this patch" questions, go to op.gg or u.gg. What an LLM is excellent at is analysis bounded by the JSON you handed it: lane decisions, item paths in this matchup, fight positioning given these comps. Stay inside the JSON and the answers stay sharp.
Found this article useful? Leave a like, and share your thoughts or questions in the comments.
EzrealThree ways to get your League of Legends match history into ChatGPT — an op.gg link, a screenshot, or text/JSON — compared. Why link-pasting quietly fails, the copy-paste steps that work, and the first prompt to send with your data.
AuroraChatGPT and Claude are excellent at LoL analysis — but they fail in five predictable ways. Here's how to neutralize each with a single prompt addition.
OriannaA field-by-field walkthrough of the JSON LoL2LLM hands to ChatGPT or Claude: how the export checkboxes map to JSON keys, a real output sample, and what to watch for when you paste it.