diff --git a/auto/autoresearch.md b/auto/autoresearch.md
new file mode 100644
index 00000000..a07a4b43
--- /dev/null
+++ b/auto/autoresearch.md
@@ -0,0 +1,60 @@
+# Autoresearch: Liquid Parse+Render Performance
+
+## Objective
+Optimize the Shopify Liquid template engine's parse and render performance.
+The workload is the ThemeRunner benchmark which parses and renders real Shopify
+theme templates (dropify, ripen, tribble, vogue) with realistic data from
+`performance/shopify/database.rb`. We measure parse time, render time, and
+object allocations. The optimization target is combined parse+render time (µs).
+
+## How to Run
+Run `./auto/autoresearch.sh` — it runs unit tests, liquid-spec conformance,
+then the performance benchmark, outputting metrics in parseable format.
+
+## Metrics
+- **Primary (optimization target)**: `combined_µs` (µs, lower is better) — sum of parse + render time
+- **Secondary (tradeoff monitoring)**:
+  - `parse_µs` — time to parse all theme templates (Liquid::Template#parse)
+  - `render_µs` — time to render all pre-compiled templates
+  - `allocations` — total object allocations for one parse+render cycle
+  Parse dominates (~70-75% of combined). Allocations correlate with GC pressure.
+
+## Files in Scope
+- `lib/liquid/*.rb` — core Liquid library (parser, lexer, context, expression, etc.)
+- `lib/liquid/tags/*.rb` — tag implementations (for, if, assign, etc.)
+- `performance/bench_quick.rb` — benchmark script
+
+## Off Limits
+- `test/` — tests must continue to pass unchanged
+- `performance/tests/` — benchmark templates, do not modify
+- `performance/shopify/` — benchmark data/filters, do not modify
+
+## Constraints
+- All unit tests must pass (`bundle exec rake base_test`)
+- liquid-spec failures must not increase beyond 2 (pre-existing UTF-8 edge cases)
+- No new gem dependencies
+- Semantic correctness must be preserved — templates must render identical output
+
+## Baseline
+- **Commit**: 4ea835a (original, before any optimizations)
+- **combined_µs**: 7,374
+- **parse_µs**: 5,928
+- **render_µs**: 1,446
+- **allocations**: 62,620
+
+## Progress Log
+- 3329b09: Replace FullToken regex with manual byte parsing → combined 7,262 (-1.5%)
+- 97e6893: Replace VariableParser regex with manual byte scanner → combined 6,945 (-5.8%), allocs 58,009
+- 2b78e4b: getbyte instead of string indexing in whitespace_handler/create_variable → allocs 51,477
+- d291e63: Lexer equal? for frozen arrays, \s+ whitespace skip → combined ~6,331
+- d79b9fa: Avoid strip alloc in Expression.parse, byteslice for strings → allocs 49,151
+- fa41224: Short-circuit parse_number with first-byte check → allocs 48,240
+- c1113ad: Fast-path String in render_obj_to_output → combined ~6,071
+- 25f9224: Fast-path simple variable parsing (skip Lexer/Parser) → combined ~5,860, allocs 45,202
+- 3939d74: Replace SIMPLE_VARIABLE regex with byte scanner → combined ~5,717, allocs 42,763
+- fe7a2f5: Fast-path simple if conditions → combined ~5,444, allocs 41,490
+- cfa0dfe: Replace For tag Syntax regex with manual byte parser → combined ~4,974, allocs 39,847
+- 8a92a4e: Unified fast-path Variable: parse name directly, only lex filter chain → combined ~5,060, allocs 40,520
+- 58d2514: parse_tag_token returns [tag_name, markup, newlines] → combined ~4,815, allocs 37,355
+- db43492: Hoist write score check out of render loop → render ~1,345
+- 17daac9: Extend fast-path to quoted string literal variables → all 1,197 variables fast-pathed
diff --git a/auto/autoresearch.sh b/auto/autoresearch.sh
new file mode 100755
index 00000000..dd79c33d
--- /dev/null
+++ b/auto/autoresearch.sh
@@ -0,0 +1,53 @@
+#!/usr/bin/env bash
+# Autoresearch benchmark runner for Liquid performance optimization
+# Runs: unit tests → liquid-spec → performance benchmark
+# Outputs METRIC lines for the agent to parse
+# Exit code 0 = all good, non-zero = broken
+set -euo pipefail
+
+cd "$(dirname "$0")/.."
+
+# ── Step 1: Unit tests (fast gate) ──────────────────────────────────
+echo "=== Unit Tests ==="
+if ! bundle exec rake base_test 2>&1; then
+  echo "FATAL: unit tests failed"
+  exit 1
+fi
+
+# ── Step 2: liquid-spec (correctness gate) ──────────────────────────
+echo ""
+echo "=== Liquid Spec ==="
+SPEC_OUTPUT=$(bundle exec liquid-spec run spec/ruby_liquid.rb 2>&1 || true)
+echo "$SPEC_OUTPUT" | tail -3
+
+# Extract failure count from "Total: N passed, N failed, N errors" line
+# Allow known pre-existing failures (≤2)
+TOTAL_LINE=$(echo "$SPEC_OUTPUT" | grep "^Total:" || echo "Total: 0 passed, 0 failed, 0 errors")
+FAILURES=$(echo "$TOTAL_LINE" | sed -n 's/.*\([0-9][0-9]*\) failed.*/\1/p')
+ERRORS=$(echo "$TOTAL_LINE" | sed -n 's/.*\([0-9][0-9]*\) error.*/\1/p')
+FAILURES=${FAILURES:-0}
+ERRORS=${ERRORS:-0}
+TOTAL_BAD=$((FAILURES + ERRORS))
+
+if [ "$TOTAL_BAD" -gt 2 ]; then
+  echo "FATAL: liquid-spec has $FAILURES failures and $ERRORS errors (threshold: 2)"
+  exit 1
+fi
+
+# ── Step 3: Performance benchmark ──────────────────────────────────
+echo ""
+echo "=== Performance Benchmark ==="
+BENCH_OUTPUT=$(bundle exec ruby performance/bench_quick.rb 2>&1)
+echo "$BENCH_OUTPUT"
+
+# Parse results and output METRIC lines
+PARSE_US=$(echo "$BENCH_OUTPUT" | grep '^parse_us=' | cut -d= -f2)
+RENDER_US=$(echo "$BENCH_OUTPUT" | grep '^render_us=' | cut -d= -f2)
+COMBINED_US=$(echo "$BENCH_OUTPUT" | grep '^combined_us=' | cut -d= -f2)
+ALLOCATIONS=$(echo "$BENCH_OUTPUT" | grep '^allocations=' | cut -d= -f2)
+
+echo ""
+echo "METRIC combined_us=$COMBINED_US"
+echo "METRIC parse_us=$PARSE_US"
+echo "METRIC render_us=$RENDER_US"
+echo "METRIC allocations=$ALLOCATIONS"
diff --git a/performance/bench_quick.rb b/performance/bench_quick.rb
index 46505913..6168f80e 100644
--- a/performance/bench_quick.rb
+++ b/performance/bench_quick.rb
@@ -9,9 +9,9 @@ RubyVM::YJIT.enable if defined?(RubyVM::YJIT)
 
 runner = ThemeRunner.new
 
-# Warmup
-5.times { runner.compile }
-5.times { runner.render }
+# Warmup — enough iterations for YJIT to fully optimize hot paths
+20.times { runner.compile }
+20.times { runner.render }
 
 GC.start
 GC.compact if GC.respond_to?(:compact)